diff --git a/.gitignore b/.gitignore index 92172f9..687ab3d 100644 --- a/.gitignore +++ b/.gitignore @@ -2,3 +2,10 @@ # v1 runtime data (DB, backups, snapshots, exports, config with secrets) data/ + +# Python +.venv/ +__pycache__/ +*.pyc +.pytest_cache/ +*.egg-info/ diff --git a/.python-version b/.python-version new file mode 100644 index 0000000..e4fba21 --- /dev/null +++ b/.python-version @@ -0,0 +1 @@ +3.12 diff --git a/CLAUDE.md b/CLAUDE.md index c4fb82c..9a90f4a 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -149,3 +149,31 @@ Don't jump phases. Phase 1 must work end-to-end before Phase 2 lands. - Inference hosting (start with a cloud API, re-evaluate later) - Character template format (during Phase 1) - Multi-session / multi-character casts: **out of scope for v1**. Leave cheap schema hooks only. + +## Phase 1 status + +Phase 1 shipped end-to-end across **35 tasks** (T0–T35). The single-bot core loop is functional: event log + projector, schema + migrations, settings/bot authoring, kickoff confirm, streaming turns, drawer rendering, regenerate/rewind, scene close + per-POV summaries, significance classifier, snapshots/backups, first-run navigation, and friendly 404/500 pages. **168 tests passing.** + +Deferred to Phase 2: second bot, group node, scene configurations, witness filtering across multi-entity scenes, activity/containers, scene-transition compression. Phase 3: event queue + triggers, time skips, active threads. Phase 4: vector retrieval, branching, surgical delete + regenerate, impact-preview UI. + +### Known v1 limitations (read before extending) + +- **Drawer edits scope**: only affinity, significance, and pin can be hand-edited from the drawer. Other v1 fields (knowledge, summary text, traits) are deferred to Phase 1.5. +- **Cold-load snapshot path** is wired and unit-tested but rarely exercised in dev — long-running sessions are the only realistic trigger. +- **WAL sidecar files** (`-wal`, `-shm`) are not captured in nightly backups; the nightly snapshot is a fresh `.backup()` so this is fine for restore but worth knowing if you copy the db file by hand. +- **HTMX SSE event names** may need a version check if you bump the htmx CDN URL in `base.html` — the swap targets are name-coupled. +- **"You" activity rows** can linger after `bot_reset` (the reset purges the bot's chats and the bot's own activity row but not the "you" row that was associated with those chats). Cosmetic, fixed in Phase 1.5. +- **Projector replay is non-idempotent** for plain `INSERT` events. After appending, call `apply_event(conn, event)` for the new row only — calling `project(conn)` re-runs every handler from scratch and will trip uniqueness or duplicate inserts. +- **8-pin auto-cap eviction** is FIFO over the auto-pinned set only. Manual pins survive the eviction; this is by design (manual intent > auto-pin signal). +- **Regenerate (T29) does not broadcast `turn_html` over SSE** — the page must refresh to show the regenerated turn. Acceptable for v1 single-tab usage; Phase 1.5 should wire the SSE event. +- **First-run middleware** fires only on bare `/` and `/chats`. Sub-paths like `/chats/` and `/chats//drawer` pass through (correct: HTMX partials should not page-redirect, and a deep-link to a missing chat should 404, not redirect mid-setup). + +### Phase 1.5 cleanup backlog + +Small follow-ups identified during Phase 1 reviews. Pick up at any time; none are blocking. + +- **`open_db` refactor.** `chat/web/bots.py:get_conn()` duplicates the context-manager body to add `check_same_thread=False`. Extend `open_db(path, *, check_same_thread=True)` and have `get_conn` call it directly — eliminates the duplicated PRAGMA setup and ensures any future PRAGMA tweak only happens in one place. +- **Regenerate broadcasts `turn_html` over SSE.** Currently a refresh is needed (see T29 limitation above). Mirror the broadcast logic from `chat/web/turns.py:post_turn` after the new `assistant_turn` lands. +- **`bot_reset` purges orphaned "you" activity rows** (see limitation above). Either delete `activity` rows by chat-membership or accept the noise indefinitely; the projection-layer fix is one extra `DELETE FROM activity WHERE entity_id='you' AND container_id IN (SELECT id FROM containers WHERE chat_id IN (...))` clause inside `_apply_bot_reset`. +- **Drawer edits for the deferred v1 fields**: edge_trust slider, edge_summary textarea, memory pov_summary textarea, knowledge_facts add/remove. The `manual_edit` projector already supports `edge_trust` / `edge_summary` / `memory_pov_summary` target_kinds — only the routes are missing. Knowledge_facts needs a new dispatch branch. +- **NICE trim order in prompt assembly** drops previous-scene first instead of last (T18 review). Greedy-cuts heuristic vs spec listing order; revisit if v1 play surfaces a real regression. diff --git a/chat/__init__.py b/chat/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/chat/app.py b/chat/app.py new file mode 100644 index 0000000..c9daf90 --- /dev/null +++ b/chat/app.py @@ -0,0 +1,134 @@ +from __future__ import annotations + +import logging +from contextlib import asynccontextmanager +from pathlib import Path + +from fastapi import FastAPI, Request +from fastapi.responses import JSONResponse +from fastapi.staticfiles import StaticFiles +from fastapi.templating import Jinja2Templates +from starlette.exceptions import HTTPException as StarletteHTTPException + +from chat.config import load_settings +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations +from chat.eventlog.log import read_events +from chat.eventlog.projector import apply_event +from chat.services.background import BackgroundWorker +from chat.services.snapshot import latest_snapshot_path, restore_from_snapshot + +# Trigger handler registration: +import chat.state.entities # noqa: F401 +import chat.state.edges # noqa: F401 +import chat.state.manual_edit # noqa: F401 +import chat.state.memory # noqa: F401 +import chat.state.world # noqa: F401 + +from chat.web.bots import router as bots_router +from chat.web.chat import router as chat_router +from chat.web.drawer import router as drawer_router +from chat.web.kickoff import router as kickoff_router +from chat.web.middleware import FirstRunRedirectMiddleware +from chat.web.nav import router as nav_router +from chat.web.settings import router as settings_router +from chat.web.sse import router as sse_router +from chat.web.turns import router as turns_router + +log = logging.getLogger(__name__) + + +@asynccontextmanager +async def lifespan(app: FastAPI): + settings = load_settings() + settings.db_path.parent.mkdir(parents=True, exist_ok=True) + apply_migrations(settings.db_path) + + # T31 cold-load fast-path: if a periodic snapshot exists, restore + # projected tables from it and replay only events past its + # ``last_event_id``. Migrations already ran above, so any new tables + # introduced after the snapshot was taken are present and empty — + # the replay-forward step refills them from the event log. + snapshot_path = latest_snapshot_path(settings.data_dir, kind="periodic") + if snapshot_path is not None: + with open_db(settings.db_path) as conn: + last_event_id = restore_from_snapshot(conn, snapshot_path) + for event in read_events( + conn, branch_id=1, after_id=last_event_id + ): + apply_event(conn, event) + log.info( + "cold-load restored from %s, replayed events past id %d", + snapshot_path, + last_event_id, + ) + + app.state.settings = settings + + # Cap concurrent Featherless connections to the account's limit + # (free / lower paid tiers cap at 2). Shared across all + # FeatherlessClient instances in the process. + from chat.llm.featherless import FeatherlessClient + + FeatherlessClient.configure_concurrency(settings.featherless_max_concurrent) + + # Background worker for the async significance pass (T22). Each job + # constructs a fresh FeatherlessClient via the factory; tests can + # disable enqueue by toggling ``app.state.background_worker.enabled``. + def _factory(): + return FeatherlessClient( + api_key=settings.featherless_api_key, + base_url=settings.featherless_base_url, + ) + + worker = BackgroundWorker(settings, llm_client_factory=_factory) + await worker.start() + app.state.background_worker = worker + + try: + yield + finally: + await worker.stop() + + +app = FastAPI(title="chat", lifespan=lifespan) +app.add_middleware(FirstRunRedirectMiddleware) + +STATIC_DIR = Path(__file__).resolve().parent / "static" +app.mount("/static", StaticFiles(directory=str(STATIC_DIR)), name="static") + +ERROR_TEMPLATES = Jinja2Templates( + directory=str(Path(__file__).resolve().parent / "templates") +) + + +@app.exception_handler(StarletteHTTPException) +async def http_exception_handler(request: Request, exc: StarletteHTTPException): + """Render a friendly HTML page for 404/500; JSON for everything else.""" + if exc.status_code in (404, 500): + return ERROR_TEMPLATES.TemplateResponse( + request, + "errors.html", + { + "status_code": exc.status_code, + "detail": exc.detail or "Something went wrong.", + "active_nav": "chats", + }, + status_code=exc.status_code, + ) + return JSONResponse(status_code=exc.status_code, content={"detail": exc.detail}) + + +app.include_router(bots_router) +app.include_router(kickoff_router) +app.include_router(settings_router) +app.include_router(nav_router) +app.include_router(chat_router) +app.include_router(drawer_router) +app.include_router(sse_router) +app.include_router(turns_router) + + +@app.get("/health") +def health(): + return {"status": "ok"} diff --git a/chat/config.py b/chat/config.py new file mode 100644 index 0000000..8eb19b6 --- /dev/null +++ b/chat/config.py @@ -0,0 +1,58 @@ +from __future__ import annotations +import os +import tomllib +from pathlib import Path +from pydantic import BaseModel, Field + +REPO_ROOT = Path(__file__).resolve().parent.parent +DEFAULT_CONFIG = REPO_ROOT / "data" / "config.toml" +DEFAULT_DB = REPO_ROOT / "data" / "chat.db" + +class Settings(BaseModel): + featherless_api_key: str + featherless_base_url: str = "https://api.featherless.ai/v1" + narrative_model: str = "dphn/Dolphin-Mistral-24B-Venice-Edition" + classifier_model: str = "NousResearch/Hermes-3-Llama-3.1-8B" + classifier_fallbacks: list[str] = Field( + default_factory=lambda: [ + "cognitivecomputations/dolphin-2.9.4-llama3-8b", + "mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated", + ] + ) + ooc_marker: str = "((" + retrieval_k: int = 4 + narrative_budget_hard: int = 8000 + narrative_budget_soft: int = 6000 + # Cap on each generated bot response. ~400 tokens ≈ 1–2 short paragraphs. + # Bump if you want longer scenes; drop to 200 for terse banter. + narrative_max_tokens: int = 400 + # Sampling temperature for narrative generation. 0.7 = grounded / + # consistent; 0.85 = creative-but-in-character (default); 1.0 = wide + # variety, can drift; >1.0 = often off-the-rails. + narrative_temperature: float = 0.85 + classifier_budget_hard: int = 4000 + classifier_timeout_s: float = 30.0 + # Featherless free tier and lower paid tiers cap concurrent connections. + # Set this to your account's max-concurrent-connections limit. + featherless_max_concurrent: int = 2 + db_path: Path = DEFAULT_DB + data_dir: Path = REPO_ROOT / "data" + bind_host: str = "127.0.0.1" + bind_port: int = 8000 + +def load_settings() -> Settings: + config_path = Path(os.environ.get("CHAT_CONFIG_PATH", DEFAULT_CONFIG)) + raw: dict = {} + if config_path.exists(): + raw = tomllib.loads(config_path.read_text()) + if "CHAT_DB_PATH" in os.environ: + raw["db_path"] = Path(os.environ["CHAT_DB_PATH"]) + if "CHAT_DATA_DIR" in os.environ: + raw["data_dir"] = Path(os.environ["CHAT_DATA_DIR"]) + elif "data_dir" not in raw and "db_path" in raw: + # T31: when ``CHAT_DB_PATH`` is overridden (typical in tests) but + # ``data_dir`` isn't, derive ``data_dir`` from the db's parent so + # snapshot/auxiliary files stay alongside the test db rather than + # leaking into the real repo data dir. + raw["data_dir"] = Path(raw["db_path"]).parent + return Settings(**raw) diff --git a/chat/db/__init__.py b/chat/db/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/chat/db/connection.py b/chat/db/connection.py new file mode 100644 index 0000000..ad21a01 --- /dev/null +++ b/chat/db/connection.py @@ -0,0 +1,17 @@ +from __future__ import annotations +import sqlite3 +from contextlib import contextmanager +from pathlib import Path + + +@contextmanager +def open_db(path: Path): + path.parent.mkdir(parents=True, exist_ok=True) + conn = sqlite3.connect(path) + conn.execute("PRAGMA journal_mode=WAL") + conn.execute("PRAGMA foreign_keys=ON") + try: + yield conn + conn.commit() + finally: + conn.close() diff --git a/chat/db/migrate.py b/chat/db/migrate.py new file mode 100644 index 0000000..95d9ba3 --- /dev/null +++ b/chat/db/migrate.py @@ -0,0 +1,26 @@ +from __future__ import annotations +from pathlib import Path + +from chat.db.connection import open_db + +MIGRATIONS_DIR = Path(__file__).parent / "migrations" + + +def apply_migrations(db_path: Path) -> None: + with open_db(db_path) as conn: + conn.execute( + "CREATE TABLE IF NOT EXISTS meta (key TEXT PRIMARY KEY, value TEXT)" + ) + cur = conn.execute("SELECT value FROM meta WHERE key = 'schema_version'") + row = cur.fetchone() + current = int(row[0]) if row else 0 + for path in sorted(MIGRATIONS_DIR.glob("*.sql")): + version = int(path.stem.split("_", 1)[0]) + if version <= current: + continue + sql = path.read_text() + conn.executescript(sql) + conn.execute( + "INSERT OR REPLACE INTO meta (key, value) VALUES ('schema_version', ?)", + (str(version),), + ) diff --git a/chat/db/migrations/0001_init_meta.sql b/chat/db/migrations/0001_init_meta.sql new file mode 100644 index 0000000..c0020e4 --- /dev/null +++ b/chat/db/migrations/0001_init_meta.sql @@ -0,0 +1,2 @@ +-- meta table is created by the migrate runner; this migration is a marker. +SELECT 1; diff --git a/chat/db/migrations/0002_classifier_failures.sql b/chat/db/migrations/0002_classifier_failures.sql new file mode 100644 index 0000000..7bfa23a --- /dev/null +++ b/chat/db/migrations/0002_classifier_failures.sql @@ -0,0 +1,8 @@ +CREATE TABLE classifier_failures ( + id INTEGER PRIMARY KEY, + kind TEXT NOT NULL, + model TEXT NOT NULL, + raw_text TEXT, + attempt_count INTEGER NOT NULL, + created_at TEXT NOT NULL DEFAULT (datetime('now')) +); diff --git a/chat/db/migrations/0003_event_log.sql b/chat/db/migrations/0003_event_log.sql new file mode 100644 index 0000000..2b4c85e --- /dev/null +++ b/chat/db/migrations/0003_event_log.sql @@ -0,0 +1,10 @@ +CREATE TABLE event_log ( + id INTEGER PRIMARY KEY, + branch_id INTEGER NOT NULL DEFAULT 1, + ts TEXT NOT NULL DEFAULT (datetime('now')), + kind TEXT NOT NULL, + payload_json TEXT NOT NULL, + superseded_by INTEGER REFERENCES event_log(id), + hidden INTEGER NOT NULL DEFAULT 0 +); +CREATE INDEX idx_event_log_branch_kind ON event_log(branch_id, kind); diff --git a/chat/db/migrations/0004_entities.sql b/chat/db/migrations/0004_entities.sql new file mode 100644 index 0000000..ef7b9f3 --- /dev/null +++ b/chat/db/migrations/0004_entities.sql @@ -0,0 +1,18 @@ +CREATE TABLE bots ( + id TEXT PRIMARY KEY, + name TEXT NOT NULL, + persona TEXT NOT NULL, + voice_samples_json TEXT NOT NULL DEFAULT '[]', + traits_json TEXT NOT NULL DEFAULT '[]', + backstory TEXT NOT NULL DEFAULT '', + initial_relationship_to_you TEXT NOT NULL DEFAULT '', + kickoff_prose TEXT NOT NULL DEFAULT '', + created_at TEXT NOT NULL DEFAULT (datetime('now')) +); + +CREATE TABLE you_entity ( + id INTEGER PRIMARY KEY CHECK (id = 1), + name TEXT NOT NULL, + pronouns TEXT NOT NULL DEFAULT '', + persona TEXT NOT NULL DEFAULT '' +); diff --git a/chat/db/migrations/0005_edges.sql b/chat/db/migrations/0005_edges.sql new file mode 100644 index 0000000..4a0969e --- /dev/null +++ b/chat/db/migrations/0005_edges.sql @@ -0,0 +1,13 @@ +CREATE TABLE edges ( + id INTEGER PRIMARY KEY, + chat_id TEXT, + source_id TEXT NOT NULL, + target_id TEXT NOT NULL, + affinity INTEGER NOT NULL DEFAULT 50, + trust INTEGER NOT NULL DEFAULT 50, + summary TEXT NOT NULL DEFAULT '', + knowledge_json TEXT NOT NULL DEFAULT '[]', + last_interaction_chat_id TEXT, + last_interaction_at TEXT, + UNIQUE (source_id, target_id) +); diff --git a/chat/db/migrations/0006_memories.sql b/chat/db/migrations/0006_memories.sql new file mode 100644 index 0000000..a9c9fa4 --- /dev/null +++ b/chat/db/migrations/0006_memories.sql @@ -0,0 +1,35 @@ +CREATE TABLE memories ( + id INTEGER PRIMARY KEY, + owner_id TEXT NOT NULL, + chat_id TEXT NOT NULL, + scene_id INTEGER, + pov_summary TEXT NOT NULL, + witness_you INTEGER NOT NULL, + witness_host INTEGER NOT NULL, + witness_guest INTEGER NOT NULL, + chat_clock_at TEXT, + source TEXT, + reliability REAL NOT NULL DEFAULT 1.0, + significance INTEGER NOT NULL DEFAULT 1, + pinned INTEGER NOT NULL DEFAULT 0, + auto_pinned INTEGER NOT NULL DEFAULT 0, + created_at TEXT NOT NULL DEFAULT (datetime('now')) +); +CREATE INDEX idx_memories_owner ON memories(owner_id); + +CREATE VIRTUAL TABLE memories_fts USING fts5( + pov_summary, content='memories', content_rowid='id' +); + +CREATE TRIGGER memories_ai AFTER INSERT ON memories BEGIN + INSERT INTO memories_fts(rowid, pov_summary) VALUES (new.id, new.pov_summary); +END; +CREATE TRIGGER memories_au AFTER UPDATE ON memories BEGIN + INSERT INTO memories_fts(memories_fts, rowid, pov_summary) + VALUES('delete', old.id, old.pov_summary); + INSERT INTO memories_fts(rowid, pov_summary) VALUES (new.id, new.pov_summary); +END; +CREATE TRIGGER memories_ad AFTER DELETE ON memories BEGIN + INSERT INTO memories_fts(memories_fts, rowid, pov_summary) + VALUES('delete', old.id, old.pov_summary); +END; diff --git a/chat/db/migrations/0007_world.sql b/chat/db/migrations/0007_world.sql new file mode 100644 index 0000000..74af990 --- /dev/null +++ b/chat/db/migrations/0007_world.sql @@ -0,0 +1,45 @@ +CREATE TABLE chats ( + id TEXT PRIMARY KEY, + host_bot_id TEXT NOT NULL, + guest_bot_id TEXT, + created_at TEXT NOT NULL DEFAULT (datetime('now')) +); + +CREATE TABLE chat_state ( + chat_id TEXT PRIMARY KEY, + time TEXT NOT NULL, + weather TEXT NOT NULL DEFAULT '', + active_scene_id INTEGER, + narrative_anchor TEXT +); + +CREATE TABLE containers ( + id INTEGER PRIMARY KEY, + chat_id TEXT NOT NULL, + name TEXT NOT NULL, + type TEXT NOT NULL, + properties_json TEXT NOT NULL DEFAULT '{}', + parent_id INTEGER REFERENCES containers(id) +); + +CREATE TABLE scenes ( + id INTEGER PRIMARY KEY, + chat_id TEXT NOT NULL, + container_id INTEGER REFERENCES containers(id), + started_at TEXT NOT NULL, + ended_at TEXT, + significance INTEGER NOT NULL DEFAULT 0, + participants_json TEXT NOT NULL DEFAULT '[]' +); + +CREATE TABLE activity ( + entity_id TEXT PRIMARY KEY, + container_id INTEGER REFERENCES containers(id), + slot TEXT, + posture TEXT NOT NULL DEFAULT '', + action_json TEXT NOT NULL DEFAULT '{}', + attention TEXT NOT NULL DEFAULT '', + holding_json TEXT NOT NULL DEFAULT '[]', + status_json TEXT NOT NULL DEFAULT '{}', + updated_at TEXT NOT NULL DEFAULT (datetime('now')) +); diff --git a/chat/eventlog/__init__.py b/chat/eventlog/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/chat/eventlog/log.py b/chat/eventlog/log.py new file mode 100644 index 0000000..ad228da --- /dev/null +++ b/chat/eventlog/log.py @@ -0,0 +1,77 @@ +from __future__ import annotations +import json +from dataclasses import dataclass +from typing import Any, Iterator +from sqlite3 import Connection + + +@dataclass +class Event: + id: int + branch_id: int + ts: str + kind: str + payload: dict[str, Any] + superseded_by: int | None + hidden: bool + + +def append_event(conn: Connection, *, kind: str, payload: dict[str, Any], branch_id: int = 1) -> int: + cur = conn.execute( + "INSERT INTO event_log (branch_id, kind, payload_json) VALUES (?, ?, ?)", + (branch_id, kind, json.dumps(payload)), + ) + return cur.lastrowid + + +def append_and_apply( + conn: Connection, + *, + kind: str, + payload: dict[str, Any], + branch_id: int = 1, +) -> int: + """Append an event AND immediately apply just that event's handler. + + Calling :func:`chat.eventlog.projector.project` after an append + re-runs every prior event, which is fine for idempotent inserts but + catastrophic for delta-shaped events like ``edge_update`` whose + handler is *not* replay-safe (each pass would re-add the same + ``affinity_delta``). This helper runs only the brand-new event + through the registered handler, leaving prior state untouched. + + No-ops cleanly when ``kind`` has no registered handler — useful for + transcript-only events like ``user_turn`` / ``assistant_turn`` where + callers may swap ``append_event`` for ``append_and_apply`` without + side effects. + """ + # Local import to avoid a circular dependency at module import: the + # projector imports from .log to define ``Event``. + from chat.eventlog.projector import apply_event + + eid = append_event(conn, kind=kind, payload=payload, branch_id=branch_id) + event = Event( + id=eid, + branch_id=branch_id, + ts="", + kind=kind, + payload=payload, + superseded_by=None, + hidden=False, + ) + apply_event(conn, event) + return eid + + +def read_events(conn: Connection, branch_id: int = 1, after_id: int = 0) -> Iterator[Event]: + cur = conn.execute( + "SELECT id, branch_id, ts, kind, payload_json, superseded_by, hidden " + "FROM event_log WHERE branch_id = ? AND id > ? AND hidden = 0 " + "AND superseded_by IS NULL ORDER BY id", + (branch_id, after_id), + ) + for row in cur: + yield Event( + id=row[0], branch_id=row[1], ts=row[2], kind=row[3], + payload=json.loads(row[4]), superseded_by=row[5], hidden=bool(row[6]), + ) diff --git a/chat/eventlog/projector.py b/chat/eventlog/projector.py new file mode 100644 index 0000000..fba406c --- /dev/null +++ b/chat/eventlog/projector.py @@ -0,0 +1,27 @@ +from __future__ import annotations +from collections.abc import Callable +from sqlite3 import Connection +from .log import Event, read_events + +Handler = Callable[[Connection, Event], None] +_REGISTRY: dict[str, Handler] = {} + + +def on(kind: str): + def deco(fn: Handler) -> Handler: + _REGISTRY[kind] = fn + return fn + return deco + + +def project(conn: Connection, branch_id: int = 1) -> None: + for event in read_events(conn, branch_id=branch_id): + h = _REGISTRY.get(event.kind) + if h: + h(conn, event) + + +def apply_event(conn: Connection, event: Event) -> None: + h = _REGISTRY.get(event.kind) + if h: + h(conn, event) diff --git a/chat/llm/__init__.py b/chat/llm/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/chat/llm/classify.py b/chat/llm/classify.py new file mode 100644 index 0000000..7074c3b --- /dev/null +++ b/chat/llm/classify.py @@ -0,0 +1,62 @@ +from __future__ import annotations +import json +import asyncio +from typing import TypeVar +from pydantic import BaseModel, ValidationError +from .client import LLMClient, Message + +T = TypeVar("T", bound=BaseModel) + +REFUSAL_PATTERNS = ("i can't", "i cannot", "i'm sorry, but", "as an ai") + + +def _strip_json_fences(text: str) -> str: + """Strip ```json ... ``` markdown fences if the model wraps its JSON output.""" + s = text.strip() + if s.startswith("```"): + # Drop the first fence line (which may be ``` or ```json) + s = s.split("\n", 1)[1] if "\n" in s else s[3:] + # Drop the trailing fence + if s.rstrip().endswith("```"): + s = s.rstrip()[:-3] + return s.strip() + + +async def classify( + client: LLMClient, + *, + model: str, + system: str, + user: str, + schema: type[T], + default: T | None = None, + timeout_s: float = 10.0, +) -> T: + schema_json = json.dumps(schema.model_json_schema(), indent=2) + schema_block = ( + f"\n\nRespond with a single JSON object matching this exact schema. " + f"Use these field names exactly; do not invent your own keys:\n```json\n{schema_json}\n```" + ) + msgs = [ + Message(role="system", content=system + schema_block), + Message(role="user", content=user), + ] + for attempt in range(3): + try: + text = await asyncio.wait_for( + client.generate(msgs, model=model, response_format={"type": "json_object"}), + timeout=timeout_s, + ) + cleaned = _strip_json_fences(text) + if any(p in cleaned.lower()[:80] for p in REFUSAL_PATTERNS) and not cleaned.lstrip().startswith("{"): + raise ValueError("refusal-shaped response") + return schema.model_validate_json(cleaned) + except (ValidationError, ValueError, json.JSONDecodeError, asyncio.TimeoutError): + msgs[0] = Message( + role="system", + content=system + schema_block + "\n\nRespond with valid JSON ONLY. No prose, no markdown fences.", + ) + continue + if default is None: + raise RuntimeError(f"classify failed for schema {schema.__name__} with no default") + return default diff --git a/chat/llm/client.py b/chat/llm/client.py new file mode 100644 index 0000000..ca34a2d --- /dev/null +++ b/chat/llm/client.py @@ -0,0 +1,14 @@ +from __future__ import annotations +from dataclasses import dataclass +from typing import Protocol, AsyncIterator, Sequence + + +@dataclass +class Message: + role: str # "system" | "user" | "assistant" + content: str + + +class LLMClient(Protocol): + async def generate(self, messages: Sequence[Message], *, model: str, **params) -> str: ... + def stream(self, messages: Sequence[Message], *, model: str, **params) -> AsyncIterator[str]: ... diff --git a/chat/llm/featherless.py b/chat/llm/featherless.py new file mode 100644 index 0000000..cf1138b --- /dev/null +++ b/chat/llm/featherless.py @@ -0,0 +1,55 @@ +from __future__ import annotations +import asyncio +from typing import AsyncIterator, Sequence +from openai import AsyncOpenAI +from .client import Message + + +class FeatherlessClient: + """Client for Featherless's OpenAI-compatible API. + + Featherless caps concurrent connections per account (2 on free / lower + paid tiers). A class-level semaphore gates every ``generate`` and + ``stream`` call so the orchestrator never exceeds the configured cap, + regardless of how many ``FeatherlessClient`` instances are alive. + + Configure once at app startup via :meth:`configure_concurrency`. The + default is 2. + """ + + _semaphore: asyncio.Semaphore | None = None + + @classmethod + def configure_concurrency(cls, max_concurrent: int) -> None: + cls._semaphore = asyncio.Semaphore(max(1, int(max_concurrent))) + + @classmethod + def _sem(cls) -> asyncio.Semaphore: + if cls._semaphore is None: + cls._semaphore = asyncio.Semaphore(2) + return cls._semaphore + + def __init__(self, api_key: str, base_url: str = "https://api.featherless.ai/v1"): + self._client = AsyncOpenAI(api_key=api_key, base_url=base_url) + + async def generate(self, messages: Sequence[Message], *, model: str, **params) -> str: + async with self._sem(): + resp = await self._client.chat.completions.create( + model=model, + messages=[{"role": m.role, "content": m.content} for m in messages], + **params, + ) + return resp.choices[0].message.content or "" + + async def stream(self, messages: Sequence[Message], *, model: str, **params) -> AsyncIterator[str]: + async with self._sem(): + stream = await self._client.chat.completions.create( + model=model, + messages=[{"role": m.role, "content": m.content} for m in messages], + stream=True, + **params, + ) + async for chunk in stream: + delta = chunk.choices[0].delta.content or "" + if delta: + yield delta diff --git a/chat/llm/mock.py b/chat/llm/mock.py new file mode 100644 index 0000000..75ab786 --- /dev/null +++ b/chat/llm/mock.py @@ -0,0 +1,16 @@ +from __future__ import annotations +from typing import AsyncIterator, Sequence +from .client import Message + + +class MockLLMClient: + def __init__(self, canned: list[str]): + self._canned = list(canned) + + async def generate(self, messages: Sequence[Message], *, model: str, **params) -> str: + return self._canned.pop(0) + + async def stream(self, messages: Sequence[Message], *, model: str, **params) -> AsyncIterator[str]: + text = self._canned.pop(0) + for ch in text: + yield ch diff --git a/chat/services/__init__.py b/chat/services/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/chat/services/background.py b/chat/services/background.py new file mode 100644 index 0000000..27eecaa --- /dev/null +++ b/chat/services/background.py @@ -0,0 +1,262 @@ +"""Async background worker for post-turn jobs (T22). + +The turn flow records a ``memory_written`` event synchronously on the +request path so the timeline updates immediately. Significance scoring is +a separate classifier round-trip that we don't want to block on, so the +turn handler enqueues a :class:`SignificanceJob` here and the worker +drains the queue out-of-band. + +A single :class:`BackgroundWorker` is started/stopped via FastAPI lifespan +in :mod:`chat.app`. The worker owns its own ``asyncio.Queue`` and runs +exactly one task that pulls jobs off the queue, calls +:func:`chat.services.significance.compute_significance`, and writes +``memory_significance_set`` (and on score 3, ``memory_pin_changed``) +events. Each job opens its own DB connection — workers and request +handlers don't share connections. + +Failures inside ``_process`` are logged and swallowed: a flaky classifier +shouldn't take down the worker. Tests can disable enqueue() by setting +``BackgroundWorker.enabled = False`` (e.g. in the existing turn-flow +fixture, which doesn't have a usable LLM key for the lifespan-managed +factory). +""" + +from __future__ import annotations + +import asyncio +import logging +from dataclasses import dataclass +from typing import Callable + +from chat.config import Settings +from chat.db.connection import open_db +from chat.eventlog.log import append_and_apply +from chat.llm.client import LLMClient +from chat.services.backup import ( + prune_backups, + should_take_backup, + take_backup, +) +from chat.services.significance import compute_significance +from chat.services.snapshot import ( + prune_periodic_snapshots, + should_take_periodic_snapshot, + take_snapshot, +) + +# T32: tick-loop wake interval. 60s gives a single backup window per +# target hour with plenty of slack: should_take_backup's 23h freshness +# guard prevents back-to-back runs. +BACKUP_TICK_INTERVAL_SECONDS = 60.0 + +log = logging.getLogger(__name__) + + +@dataclass +class SignificanceJob: + """One unit of work for the background worker. + + ``host_bot_id`` is the memory's owner — used both for the auto-pin + soft cap query and as the eventual scope for the soft-cap eviction. + """ + + memory_id: int + narrative_text: str + prior_dialogue: list[dict] + host_bot_id: str + + +class BackgroundWorker: + """asyncio.Queue-backed single-worker task. + + Started on app startup; ``stop()`` enqueues a sentinel and awaits the + task so any in-flight job has a chance to finish. Pending jobs after + the sentinel are dropped on shutdown — Phase 1 simplification. + """ + + def __init__( + self, + settings: Settings, + llm_client_factory: Callable[[], LLMClient], + *, + enabled: bool = True, + ) -> None: + self._settings = settings + self._llm_client_factory = llm_client_factory + self._queue: asyncio.Queue[SignificanceJob | None] = asyncio.Queue() + self._task: asyncio.Task | None = None + # T32: nightly-backup tick loop runs alongside the job loop. The + # event is set by stop() to wake the loop early so shutdown is + # snappy even mid-tick. + self._tick_task: asyncio.Task | None = None + self._tick_stop: asyncio.Event = asyncio.Event() + self.enabled = enabled + + async def start(self) -> None: + if self._task is not None: + return + self._task = asyncio.create_task(self._run()) + self._tick_task = asyncio.create_task(self._tick_loop()) + + async def stop(self) -> None: + # Stop the tick loop first — it has no in-flight work to drain, + # so signalling early lets it exit while the job loop is still + # finishing its sentinel handoff. + self._tick_stop.set() + if self._tick_task is not None: + await self._tick_task + self._tick_task = None + if self._task is None: + return + await self._queue.put(None) # sentinel + await self._task + self._task = None + + def enqueue(self, job: SignificanceJob) -> None: + if not self.enabled: + return + self._queue.put_nowait(job) + + async def _run(self) -> None: + while True: + job = await self._queue.get() + if job is None: + return + try: + await self._process(job) + except Exception as exc: # noqa: BLE001 — worker must not die + log.exception("significance job failed: %s", exc) + + async def _tick_loop(self) -> None: + """Periodic-operations loop (T32 nightly backup). + + Wakes every :data:`BACKUP_TICK_INTERVAL_SECONDS` seconds and + asks :func:`should_take_backup` whether a backup is due. The + scheduling decision lives in the backup module so we don't + duplicate the "is it 03:00?" logic here. Failures are caught + and logged so a flaky disk doesn't kill the loop — the next + tick will retry. + + Wait uses :func:`asyncio.wait_for` on ``_tick_stop`` so that + :meth:`stop` can interrupt a sleeping tick instead of having to + wait the full interval. + """ + while not self._tick_stop.is_set(): + try: + if should_take_backup(self._settings.data_dir): + take_backup( + db_path=self._settings.db_path, + data_dir=self._settings.data_dir, + ) + prune_backups(self._settings.data_dir, keep=14) + log.info("nightly backup taken") + except Exception as exc: # noqa: BLE001 — never break the loop + log.exception("backup tick failed: %s", exc) + try: + await asyncio.wait_for( + self._tick_stop.wait(), + timeout=BACKUP_TICK_INTERVAL_SECONDS, + ) + except asyncio.TimeoutError: + # Normal path: timed out waiting for stop, run another tick. + pass + + async def _process(self, job: SignificanceJob) -> None: + client = self._llm_client_factory() + score = await compute_significance( + client, + model=self._settings.classifier_model, + narrative_text=job.narrative_text, + prior_dialogue=job.prior_dialogue, + ) + with open_db(self._settings.db_path) as conn: + append_and_apply( + conn, + kind="memory_significance_set", + payload={ + "memory_id": job.memory_id, + "significance": score, + }, + ) + if score >= 3: + _auto_pin_with_cap( + conn, + owner_id=job.host_bot_id, + memory_id=job.memory_id, + ) + + # T31: piggy-back the periodic snapshot check on the background + # worker so we don't need a separate timer task. The classifier + # pass already runs out-of-band, so snapshot I/O on the same + # worker is a natural fit. Each snapshot opens its own + # connection so we don't conflate the snapshot's read-only view + # with the significance-write transaction above. Failures are + # caught and logged: a flaky disk shouldn't take down the + # significance pipeline. + try: + with open_db(self._settings.db_path) as conn: + if should_take_periodic_snapshot( + conn, self._settings.data_dir + ): + snapshot_path = take_snapshot( + conn, + data_dir=self._settings.data_dir, + kind="periodic", + ) + prune_periodic_snapshots( + self._settings.data_dir, keep=5 + ) + log.info( + "periodic snapshot taken: %s", snapshot_path + ) + except Exception as exc: # noqa: BLE001 — never break the worker + log.exception("periodic snapshot failed: %s", exc) + + +def _auto_pin_with_cap( + conn, + *, + owner_id: str, + memory_id: int, + cap: int = 8, +) -> None: + """Auto-pin ``memory_id`` and evict the oldest auto-pin if over ``cap``. + + Per §8.5: pivotal turns are auto-pinned, with a soft cap of 8 pins per + bot. When the cap is exceeded the oldest auto-pin is unpinned (manual + pins are never auto-evicted — we filter on ``auto_pinned = 1``). + """ + append_and_apply( + conn, + kind="memory_pin_changed", + payload={ + "memory_id": memory_id, + "pinned": 1, + "auto_pinned": 1, + }, + ) + cur = conn.execute( + "SELECT COUNT(*) FROM memories WHERE owner_id = ? AND pinned = 1", + (owner_id,), + ) + count = cur.fetchone()[0] + if count <= cap: + return + cur = conn.execute( + "SELECT id FROM memories " + "WHERE owner_id = ? AND pinned = 1 AND auto_pinned = 1 AND id != ? " + "ORDER BY created_at ASC, id ASC LIMIT 1", + (owner_id, memory_id), + ) + row = cur.fetchone() + if row is None: + return + append_and_apply( + conn, + kind="memory_pin_changed", + payload={ + "memory_id": row[0], + "pinned": 0, + "auto_pinned": 0, + }, + ) diff --git a/chat/services/backup.py b/chat/services/backup.py new file mode 100644 index 0000000..d8b2f4e --- /dev/null +++ b/chat/services/backup.py @@ -0,0 +1,106 @@ +"""Nightly DB backup service (T32, Requirements §12). + +A simple in-process scheduler: at 03:00 local time daily, copy +``chat.db`` to ``data/backups/chat-.db`` and prune to the +14 most recent. The BackgroundWorker tick loop calls +:func:`should_take_backup` every 60 seconds; when it returns True the +worker calls :func:`take_backup` then :func:`prune_backups`. + +The launchd plist suggested in §12 can replace this later by invoking a +small script that calls :func:`take_backup` directly. For v1 the +in-process loop is enough — the daemon already runs continuously to +serve requests, so there's no extra moving part to install. + +Backups capture the live ``.db`` file via :func:`shutil.copy2`. SQLite's +WAL mode means an in-flight transaction's pages might live in the +``-wal`` sidecar rather than the main file, but our codebase commits +every write transaction synchronously, so the .db alone is sufficient +for v1. A truly safe online backup would use +``sqlite3.Connection.backup()``; deferred. +""" + +from __future__ import annotations + +import shutil +from datetime import datetime, timezone +from pathlib import Path + +# 03:00 local time per Requirements §12. Hardcoded for v1 — making this +# configurable via Settings is straightforward but not needed yet. +DEFAULT_BACKUP_HOUR = 3 + +# Retention window per Requirements §12 ("Last 14 retained"). +DEFAULT_KEEP = 14 + +# Wake interval for should_take_backup's freshness check. We wake the +# tick loop every 60s, so a backup taken in the previous tick within the +# same target hour must NOT trigger another. 23h gives us a generous +# safety margin against scheduling jitter while still allowing a single +# backup per day. +FRESHNESS_HOURS = 23 + + +def take_backup(*, db_path: Path, data_dir: Path) -> Path: + """Copy ``db_path`` to ``data_dir/backups/chat-.db``. + + Returns the new file path. Creates the backup directory if missing. + Uses :func:`shutil.copy2` so the destination's mtime is preserved — + :func:`should_take_backup` reads mtime to gate fresh backups. + """ + backup_dir = data_dir / "backups" + backup_dir.mkdir(parents=True, exist_ok=True) + timestamp = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ") + backup_path = backup_dir / f"chat-{timestamp}.db" + shutil.copy2(db_path, backup_path) + return backup_path + + +def prune_backups(data_dir: Path, *, keep: int = DEFAULT_KEEP) -> int: + """Remove all but the most recent ``keep`` backup files. + + Returns the number of files removed. Safe when the directory is + missing (returns 0). Sorting is by filename, which is the UTC + timestamp embedded in the name — lexicographic order matches + chronological order. + """ + backup_dir = data_dir / "backups" + if not backup_dir.exists(): + return 0 + files = sorted(backup_dir.glob("chat-*.db")) + to_remove = files[:-keep] if len(files) > keep else [] + for f in to_remove: + f.unlink() + return len(to_remove) + + +def should_take_backup( + data_dir: Path, *, target_hour: int = DEFAULT_BACKUP_HOUR +) -> bool: + """Decide whether a nightly backup is due. + + Two conditions must hold: + + * The current local hour matches ``target_hour``. + * No backup file in ``data_dir/backups/`` has an mtime within the + last :data:`FRESHNESS_HOURS` (23h). The 23h window prevents a + double-backup within the same target hour while still allowing + the next day's run to fire on time. + + Local time (not UTC) is used for the hour comparison per the + requirements ("03:00 local time"). The filename embeds a UTC stamp + so file ordering remains unambiguous across DST transitions. + """ + now = datetime.now() + if now.hour != target_hour: + return False + backup_dir = data_dir / "backups" + if not backup_dir.exists(): + return True + files = list(backup_dir.glob("chat-*.db")) + if not files: + return True + most_recent = max(files, key=lambda f: f.stat().st_mtime) + age_hours = ( + datetime.now().timestamp() - most_recent.stat().st_mtime + ) / 3600 + return age_hours >= FRESHNESS_HOURS diff --git a/chat/services/kickoff.py b/chat/services/kickoff.py new file mode 100644 index 0000000..a5540bf --- /dev/null +++ b/chat/services/kickoff.py @@ -0,0 +1,150 @@ +"""Kickoff prose parser. + +Service-layer function that converts a bot's authored kickoff prose into a +structured ``KickoffParse`` for the kickoff confirm-and-edit step (T13 will +wire this into the UI flow). + +The classifier prompt includes only the bot context that's load-bearing for +parsing the opening scene: name, persona, the authored +``initial_relationship_to_you`` blurb, the ``you`` entity name, and the +kickoff prose itself. Other identity fields (traits, backstory, ...) are +intentionally left out — they would be noise for this extraction. +""" + +from __future__ import annotations + +from pydantic import BaseModel, Field + +from chat.llm.classify import classify +from chat.llm.client import LLMClient + + +class ActivityShape(BaseModel): + """Per-entity activity at scene start. + + Maps onto Requirements §6.5: ``current_action.{verb,interruptible, + required_attention,expected_duration}`` plus posture, attention, holding. + ``action_required_attention`` is left as a free-form string ("low" / + "medium" / "high" expected) rather than a Literal so the classifier has + room to vary phrasing in v1. + """ + + posture: str + action_verb: str + action_interruptible: bool + action_required_attention: str # low | medium | high + action_expected_duration: str + attention: str = "" + holding: list[str] = Field(default_factory=list) + + +class KickoffParse(BaseModel): + """Structured opening-scene state extracted from kickoff prose. + + ``container_properties`` is loose ``dict``: the classifier may emit + ``moving`` / ``public`` / ``audible_range`` keys, but downstream + consumers (T13's confirm form) handle missing keys gracefully. + ``initial_time_iso`` is stored as text — not validated as a datetime + here; ``chat_state.time`` stores it as a plain string. + """ + + container_name: str + container_type: str + container_properties: dict + you_activity: ActivityShape + bot_activity: ActivityShape + initial_time_iso: str + edge_seed_summary: str + edge_seed_knowledge_facts: list[str] + + +_SYSTEM_PROMPT = ( + "You are extracting structured scene state from a roleplay kickoff " + "scene description. The user provides bot context and a prose " + "description of the opening scene; you output JSON conforming to the " + "schema. Be concrete: pick a single container, single activity per " + "entity, and a sensible initial in-fiction time. Anything not stated " + "explicitly should be inferred reasonably from the prose." +) + + +def _build_user_prompt( + *, + bot_name: str, + bot_persona: str, + initial_relationship_to_you: str, + kickoff_prose: str, + you_name: str, +) -> str: + return ( + f"BOT NAME: {bot_name}\n" + f"BOT PERSONA: {bot_persona}\n" + f"INITIAL RELATIONSHIP TO {you_name}: {initial_relationship_to_you}\n" + f"YOU NAME: {you_name}\n" + f"KICKOFF PROSE:\n{kickoff_prose}" + ) + + +def _empty_activity() -> ActivityShape: + return ActivityShape( + posture="", + action_verb="", + action_interruptible=True, + action_required_attention="low", + action_expected_duration="brief", + ) + + +def _empty_kickoff_parse() -> KickoffParse: + """Default returned when the classifier can't produce a valid parse. + + The user gets a mostly-empty confirm form they can fill in by hand + instead of a 500. ``initial_time_iso`` is left as the current UTC. + """ + from datetime import datetime, timezone + + return KickoffParse( + container_name="", + container_type="", + container_properties={}, + you_activity=_empty_activity(), + bot_activity=_empty_activity(), + initial_time_iso=datetime.now(timezone.utc).isoformat(timespec="seconds"), + edge_seed_summary="", + edge_seed_knowledge_facts=[], + ) + + +async def parse_kickoff( + client: LLMClient, + *, + model: str, + bot_name: str, + bot_persona: str, + initial_relationship_to_you: str, + kickoff_prose: str, + you_name: str, + timeout_s: float = 10.0, +) -> KickoffParse: + """Parse authored kickoff prose into a structured ``KickoffParse``. + + Falls back to a mostly-empty default if the classifier fails — the + confirm-and-edit form is the human-in-the-loop, so a degraded form + that the user can fill in is preferable to a 500. + """ + user_prompt = _build_user_prompt( + bot_name=bot_name, + bot_persona=bot_persona, + initial_relationship_to_you=initial_relationship_to_you, + kickoff_prose=kickoff_prose, + you_name=you_name, + ) + return await classify( + client, + model=model, + system=_SYSTEM_PROMPT, + user=user_prompt, + schema=KickoffParse, + default=_empty_kickoff_parse(), + timeout_s=timeout_s, + ) diff --git a/chat/services/memory_write.py b/chat/services/memory_write.py new file mode 100644 index 0000000..3ca40c5 --- /dev/null +++ b/chat/services/memory_write.py @@ -0,0 +1,78 @@ +"""Per-turn memory writes (T21). + +After ``assistant_turn`` lands, the turn flow records a ``memory_written`` +event for each present POV owner. Phase 1 single-bot turns only have the +host bot as a memory-store owner — ``you`` doesn't have a memory store in +v1 — so we write exactly one row per turn. + +Phase 1 simplifications (per plan §11.1, T27 will refine): + +- ``pov_summary`` is the assistant's raw narrative text. T27 rewrites at + scene close into per-POV summary form. +- ``significance`` defaults to ``1`` (Notable). T22's async significance + pass overwrites via a follow-up event. +- Witness flags are hard-coded ``[you=1, host=1, guest=0]``. Phase 2 will + derive them from ``chat.guest_bot_id`` once a guest can be present. +""" + +from __future__ import annotations + +from sqlite3 import Connection + +from chat.eventlog.log import append_and_apply + + +def record_turn_memory( + conn: Connection, + *, + chat_id: str, + host_bot_id: str, + narrative_text: str, + scene_id: int | None = None, + chat_clock_at: str | None = None, + source: str = "direct", + significance: int = 1, +) -> tuple[int, int | None]: + """Append a ``memory_written`` event for the host bot's POV of this turn. + + Uses :func:`chat.eventlog.log.append_and_apply` (not raw + :func:`append_event`) so the new memory row is projected immediately + without re-running prior non-idempotent handlers (e.g. ``edge_update`` + deltas). + + Returns ``(event_id, memory_id)``. ``event_id`` is the row id of the + just-appended ``memory_written`` event in ``event_log``. ``memory_id`` + is the autoincrement PK of the corresponding ``memories`` row — these + are *different* numbers (event_log and memories use independent + rowid sequences) so callers needing to update significance or pin + state must use ``memory_id``. Falls back to ``None`` if the projected + row can't be located, which shouldn't happen but keeps the return + shape stable. + """ + payload: dict = { + "owner_id": host_bot_id, + "chat_id": chat_id, + "pov_summary": narrative_text, + "witness_you": 1, + "witness_host": 1, + "witness_guest": 0, + "source": source, + "reliability": 1.0, + "significance": significance, + "pinned": 0, + "auto_pinned": 0, + } + if scene_id is not None: + payload["scene_id"] = scene_id + if chat_clock_at is not None: + payload["chat_clock_at"] = chat_clock_at + + event_id = append_and_apply(conn, kind="memory_written", payload=payload) + row = conn.execute( + "SELECT id FROM memories " + "WHERE owner_id = ? AND chat_id = ? " + "ORDER BY id DESC LIMIT 1", + (host_bot_id, chat_id), + ).fetchone() + memory_id = row[0] if row else None + return event_id, memory_id diff --git a/chat/services/prompt.py b/chat/services/prompt.py new file mode 100644 index 0000000..1df074b --- /dev/null +++ b/chat/services/prompt.py @@ -0,0 +1,556 @@ +"""Narrative-prompt assembly with must/should/nice trim tiers. + +Implements Task 18 (Phase 1D). See Requirements §3.2 (token budgets and +trim tiers) and §6.3 (speaker prompt assembly order). The function +:func:`assemble_narrative_prompt` returns a list of +:class:`chat.llm.client.Message` objects ready to feed to +``LLMClient.generate``. + +Trim policy when the assembled prompt exceeds the soft target: + +- **MUST-include** (never trimmed): system / speaker identity, the + speaker→addressee edge, the activity snapshot for all present + entities, the current scene description, and the last 4 turns of + dialogue. +- **SHOULD-include** (trim when over budget): other edges of the + speaker. (Group nodes, active threads, and active events / props are + Phase 3 — skipped here.) +- **NICE-include** (trim first): retrieved memories beyond top-2, + dialogue turns beyond the last 4 (replaced with a one-line elision + placeholder), per-POV summary of the previous scene. + +Token counting uses ``tiktoken.get_encoding("cl100k_base")`` per the +requirements. Mistral / Llama tokenizers diverge ~5%; we accept the +drift. + +The function is intentionally deterministic (no LLM call) so it is +testable with synthetic state and so T29's regenerate flow can rebuild +prompts without re-running classifiers. +""" + +from __future__ import annotations + +from sqlite3 import Connection + +import tiktoken + +from chat.llm.client import Message +from chat.state.edges import get_edge, list_edges_for +from chat.state.entities import get_bot, get_you +from chat.state.memory import search_memories +from chat.state.world import ( + active_scene, + get_activity, + get_chat, + get_container, + get_scene, +) + + +# Cache the encoder once at import-time. tiktoken's encoder load is +# non-trivial (~tens of ms) and the encoding is process-wide stable. +_ENCODER = tiktoken.get_encoding("cl100k_base") + + +# --------------------------------------------------------------------------- +# Helpers +# --------------------------------------------------------------------------- + + +def _count_tokens(text: str, encoding=_ENCODER) -> int: + """Return the cl100k_base token count for ``text`` (0 for falsy).""" + if not text: + return 0 + return len(encoding.encode(text)) + + +def _build_speaker_identity(bot: dict) -> str: + """Render the bot identity block. Skips empty optional fields.""" + lines = [f"You are {bot['name']}."] + if bot.get("persona"): + lines.append("") + lines.append("PERSONA:") + lines.append(bot["persona"]) + voice_samples = bot.get("voice_samples") or [] + if voice_samples: + lines.append("") + lines.append("VOICE REFERENCE:") + lines.append("\n---\n".join(voice_samples)) + traits = bot.get("traits") or [] + if traits: + lines.append("") + lines.append(f"TRAITS: {', '.join(traits)}") + if bot.get("backstory"): + lines.append("") + lines.append("BACKSTORY:") + lines.append(bot["backstory"]) + return "\n".join(lines) + + +def _build_edge_block(edge: dict | None, addressee_name: str) -> str | None: + """Render the speaker → addressee edge. Returns None when no edge exists.""" + if edge is None: + return None + lines = [f"YOUR EDGE TO {addressee_name}:"] + lines.append(f"- Affinity: {edge.get('affinity', 50)}/100") + lines.append(f"- Trust: {edge.get('trust', 50)}/100") + summary = edge.get("summary") or "" + if summary: + lines.append(f"- Summary: {summary}") + knowledge = edge.get("knowledge") or [] + if knowledge: + lines.append(f"- What you know about {addressee_name}:") + for fact in knowledge: + lines.append(f" * {fact}") + return "\n".join(lines) + + +def _build_activity_block(activities: list[dict]) -> str | None: + """Render the activity snapshot for all present entities.""" + rendered: list[str] = [] + for a in activities: + if a is None: + continue + label = a.get("_display_name") or a.get("entity_id", "?") + parts: list[str] = [] + posture = a.get("posture") or "" + if posture: + parts.append(posture) + action = a.get("action") or {} + verb = action.get("verb") if isinstance(action, dict) else None + if verb: + parts.append(verb) + attention = a.get("attention") or "" + if attention: + parts.append(f"attention: {attention}") + holding = a.get("holding") or [] + if holding: + parts.append(f"holding: {', '.join(holding)}") + if parts: + rendered.append(f"- {label}: " + ", ".join(parts)) + else: + rendered.append(f"- {label}: (no activity recorded)") + if not rendered: + return None + return "ACTIVITIES:\n" + "\n".join(rendered) + + +def _build_scene_block(chat: dict, container: dict | None, scene: dict | None) -> str | None: + """Render the current-scene block. Always present when chat exists.""" + lines = ["CURRENT SCENE:"] + if container is not None: + lines.append(f"- Container: {container['name']} ({container['type']})") + chat_time = chat.get("time") if chat else None + if chat_time: + lines.append(f"- Time: {chat_time}") + if scene is not None and scene.get("started_at"): + lines.append(f"- Active scene started: {scene['started_at']}") + if len(lines) == 1: + return None + return "\n".join(lines) + + +def _format_dialogue_turn(turn: dict) -> str: + speaker = turn.get("speaker") or "?" + text = turn.get("text") or "" + return f"{speaker}: {text}" + + +def _build_dialogue_block( + recent: list[dict], + earlier_summary: str | None, +) -> str | None: + """Render the recent-dialogue block. The ``recent`` list is the + *kept* tail of the dialogue (already trimmed to the last-N turns). + ``earlier_summary``, when non-None, is rendered as the first line as + ``earlier: `` to flag elided context. + """ + if not recent and not earlier_summary: + return None + lines = ["RECENT DIALOGUE:"] + if earlier_summary: + lines.append(f"earlier: {earlier_summary}") + for turn in recent: + lines.append(_format_dialogue_turn(turn)) + return "\n".join(lines) + + +def _build_memories_block(memory_summaries: list[str]) -> str | None: + if not memory_summaries: + return None + lines = ["RELEVANT MEMORIES:"] + for m in memory_summaries: + lines.append(f"- {m}") + return "\n".join(lines) + + +def _build_other_edges_block(edges: list[dict]) -> str | None: + """Render edges to entities other than the addressee.""" + if not edges: + return None + lines = ["OTHER EDGES:"] + for e in edges: + target = e.get("_display_name") or e.get("target_id", "?") + affinity = e.get("affinity", 50) + trust = e.get("trust", 50) + lines.append(f"- {target}: affinity {affinity}/100, trust {trust}/100") + summary = e.get("summary") or "" + if summary: + lines.append(f" summary: {summary}") + return "\n".join(lines) + + +def _build_previous_scene_block(pov_summary: str | None) -> str | None: + if not pov_summary: + return None + return "PREVIOUS SCENE SUMMARY:\n" + pov_summary + + +def _closing_instruction(speaker_name: str, addressee_name: str) -> str: + return ( + f"Continue the scene as {speaker_name}, in their voice, responding " + "naturally. Use *asterisks* for actions and quotes for dialogue. " + f"Stay in character. Do not narrate {addressee_name}'s actions or " + "thoughts. " + "Keep your response to a single beat — one or two short paragraphs " + "at most. Don't monologue; leave room for the other person to react." + ) + + +def _join_blocks(blocks: list[str | None]) -> str: + """Join non-empty blocks with double newlines.""" + return "\n\n".join(b for b in blocks if b) + + +def _earlier_summary_placeholder(elided_count: int) -> str: + """Phase 1 placeholder. Real summarization is a downstream concern.""" + plural = "turn" if elided_count == 1 else "turns" + return f"{elided_count} earlier {plural} elided for brevity" + + +def _resolve_previous_scene_summary( + conn: Connection, chat_id: str, speaker_bot_id: str +) -> str | None: + """Return ``pov_summary`` of the most recent ended scene, owned by + the speaker. None if no closed scene exists or no matching memory. + """ + row = conn.execute( + "SELECT id FROM scenes WHERE chat_id = ? AND ended_at IS NOT NULL " + "ORDER BY ended_at DESC LIMIT 1", + (chat_id,), + ).fetchone() + if not row: + return None + scene_id = row[0] + mem = conn.execute( + "SELECT pov_summary FROM memories WHERE scene_id = ? AND owner_id = ? " + "ORDER BY id DESC LIMIT 1", + (scene_id, speaker_bot_id), + ).fetchone() + if not mem: + return None + return mem[0] + + +def _resolve_addressee( + conn: Connection, addressee: str, you: dict | None +) -> tuple[str, str]: + """Return ``(addressee_id, addressee_display_name)``. + + The function is permissive: ``addressee="you"`` resolves to the + you-entity (display name is its authored name, falling back to + "you" if no entity exists yet). Other ids resolve as bot ids. + """ + if addressee == "you": + name = (you or {}).get("name") or "you" + return "you", name + bot = get_bot(conn, addressee) + if bot is not None: + return addressee, bot["name"] + return addressee, addressee + + +# --------------------------------------------------------------------------- +# Public API +# --------------------------------------------------------------------------- + + +def assemble_narrative_prompt( + conn: Connection, + *, + chat_id: str, + speaker_bot_id: str, + addressee: str = "you", + user_turn_prose: str | None = None, + recent_dialogue: list[dict] | None = None, + retrieved_memory_summaries: list[str] | None = None, + budget_soft: int = 6000, + budget_hard: int = 8000, + encoding_name: str = "cl100k_base", +) -> list[Message]: + """Assemble the narrative prompt for ``speaker_bot_id`` to respond. + + Returns a list of :class:`Message` objects: one ``system`` message + carrying the assembled context, optionally followed by a single + ``user`` message containing ``user_turn_prose`` (when provided). + + Trimming proceeds in tiers (NICE → SHOULD) once the total token + count exceeds ``budget_soft``; the function refuses to exceed + ``budget_hard``. If the MUST-include block alone is already over + ``budget_hard``, :class:`ValueError` is raised — the caller should + surface the failure rather than ship a malformed prompt. + """ + encoding = ( + _ENCODER if encoding_name == "cl100k_base" + else tiktoken.get_encoding(encoding_name) + ) + + bot = get_bot(conn, speaker_bot_id) + if bot is None: + raise ValueError(f"speaker_bot_id {speaker_bot_id!r} not found") + + chat = get_chat(conn, chat_id) + if chat is None: + raise ValueError(f"chat_id {chat_id!r} not found") + + you = get_you(conn) + addressee_id, addressee_name = _resolve_addressee(conn, addressee, you) + + # ---- Build all components as text strings ------------------------------ + + speaker_identity = _build_speaker_identity(bot) + + edge_to_addressee = _build_edge_block( + get_edge(conn, speaker_bot_id, addressee_id), + addressee_name, + ) + + # Activity for present entities. Phase 1: you + speaker bot. (When a + # guest is added in Phase 1+, callers that know about it can pass + # extra activities via a future hook; for now we keep it strict.) + activities: list[dict] = [] + you_act = get_activity(conn, "you") + if you_act is not None: + you_act = dict(you_act) + you_act["_display_name"] = (you or {}).get("name") or "you" + activities.append(you_act) + bot_act = get_activity(conn, speaker_bot_id) + if bot_act is not None: + bot_act = dict(bot_act) + bot_act["_display_name"] = bot["name"] + activities.append(bot_act) + activity_block = _build_activity_block(activities) + + container = None + if chat.get("active_scene_id"): + scene = get_scene(conn, chat["active_scene_id"]) + if scene and scene.get("container_id"): + container = get_container(conn, scene["container_id"]) + else: + scene = active_scene(conn, chat_id) + if container is None and scene and scene.get("container_id"): + container = get_container(conn, scene["container_id"]) + scene_block = _build_scene_block(chat, container, scene) + + # Other edges: speaker → non-addressee. + all_outgoing = list_edges_for(conn, speaker_bot_id) + other_edges_raw = [e for e in all_outgoing if e.get("target_id") != addressee_id] + for e in other_edges_raw: + tid = e.get("target_id") + if tid == "you": + e["_display_name"] = (you or {}).get("name") or "you" + else: + tb = get_bot(conn, tid) if tid else None + e["_display_name"] = tb["name"] if tb else (tid or "?") + other_edges_block = _build_other_edges_block(other_edges_raw) + + # Memories: caller override wins; otherwise FTS5 search keyed on the + # scene's container/posture as a coarse query proxy. + if retrieved_memory_summaries is not None: + memory_summaries = list(retrieved_memory_summaries) + else: + query = (container or {}).get("name") or chat.get("narrative_anchor") or "" + memory_summaries = [] + if query: + try: + hits = search_memories(conn, speaker_bot_id, "host", query, k=4) + memory_summaries = [h["pov_summary"] for h in hits] + except Exception: + memory_summaries = [] + + # Dialogue: caller override only (no event_log read in Phase 1). + dialogue_full = list(recent_dialogue or []) + + previous_scene_summary = _resolve_previous_scene_summary( + conn, chat_id, speaker_bot_id + ) + + closing = _closing_instruction(bot["name"], addressee_name) + + # ---- Build the MUST core ---------------------------------------------- + + last4 = dialogue_full[-4:] if dialogue_full else [] + must_dialogue_block = _build_dialogue_block(last4, earlier_summary=None) + + must_blocks: list[str | None] = [ + speaker_identity, + edge_to_addressee, + scene_block, + activity_block, + must_dialogue_block, + closing, + ] + must_text = _join_blocks(must_blocks) + must_tokens = _count_tokens(must_text, encoding) + if must_tokens > budget_hard: + raise ValueError( + f"MUST-include block ({must_tokens} tokens) exceeds budget_hard " + f"({budget_hard}). Cannot assemble prompt." + ) + + # ---- Stage SHOULD additions, then NICE additions ----------------------- + + # We carry a running "components" list and rebuild the body as we go + # so token accounting reflects join-overhead. Order in the final + # prompt follows §6.3: identity → edge → other edges → scene → + # activities → previous scene summary → memories → dialogue → close. + + def assemble( + *, + include_other_edges: bool, + include_previous_scene: bool, + include_memories_top_k: int, + dialogue_keep: int, + ) -> tuple[str, int, list[dict]]: + # dialogue: keep the last `dialogue_keep` turns verbatim; older + # turns become an "earlier:" placeholder line. + kept_dialogue = ( + dialogue_full[-dialogue_keep:] if dialogue_keep > 0 else [] + ) + elided = max(0, len(dialogue_full) - len(kept_dialogue)) + earlier_summary = ( + _earlier_summary_placeholder(elided) if elided > 0 else None + ) + dialogue_block = _build_dialogue_block(kept_dialogue, earlier_summary) + + memories_subset = memory_summaries[:include_memories_top_k] + memories_block = _build_memories_block(memories_subset) + + prev_block = ( + _build_previous_scene_block(previous_scene_summary) + if include_previous_scene else None + ) + + body = _join_blocks([ + speaker_identity, + edge_to_addressee, + other_edges_block if include_other_edges else None, + scene_block, + activity_block, + prev_block, + memories_block, + dialogue_block, + closing, + ]) + return body, _count_tokens(body, encoding), kept_dialogue + + # Start with the MUST baseline: last 4 turns of dialogue, no + # SHOULD/NICE extras. + baseline_keep = min(4, len(dialogue_full)) + + # Try the most generous configuration first; trim greedily. + nice_dialogue_keep = len(dialogue_full) # all turns, no elision + nice_memories_k = min(4, len(memory_summaries)) + include_prev = previous_scene_summary is not None + include_other = other_edges_block is not None + + body, total, _ = assemble( + include_other_edges=include_other, + include_previous_scene=include_prev, + include_memories_top_k=nice_memories_k, + dialogue_keep=nice_dialogue_keep, + ) + + # If under soft, we're done. + if total <= budget_soft: + return _emit(body, user_turn_prose) + + # Drop NICE in order: previous scene → memories beyond top-2 → + # older dialogue turns (collapse to 4). + if include_prev: + body, total, _ = assemble( + include_other_edges=include_other, + include_previous_scene=False, + include_memories_top_k=nice_memories_k, + dialogue_keep=nice_dialogue_keep, + ) + include_prev = False + if total <= budget_soft: + return _emit(body, user_turn_prose) + + if nice_memories_k > 2: + nice_memories_k = 2 + body, total, _ = assemble( + include_other_edges=include_other, + include_previous_scene=False, + include_memories_top_k=nice_memories_k, + dialogue_keep=nice_dialogue_keep, + ) + if total <= budget_soft: + return _emit(body, user_turn_prose) + + if nice_dialogue_keep > baseline_keep: + nice_dialogue_keep = baseline_keep + body, total, _ = assemble( + include_other_edges=include_other, + include_previous_scene=False, + include_memories_top_k=nice_memories_k, + dialogue_keep=nice_dialogue_keep, + ) + if total <= budget_soft: + return _emit(body, user_turn_prose) + + # Drop more NICE until we're under hard: memories all the way to 0. + while nice_memories_k > 0 and total > budget_hard: + nice_memories_k = max(0, nice_memories_k - 1) + body, total, _ = assemble( + include_other_edges=include_other, + include_previous_scene=False, + include_memories_top_k=nice_memories_k, + dialogue_keep=nice_dialogue_keep, + ) + + # Drop SHOULD: other edges. + if include_other and total > budget_hard: + include_other = False + body, total, _ = assemble( + include_other_edges=False, + include_previous_scene=False, + include_memories_top_k=nice_memories_k, + dialogue_keep=nice_dialogue_keep, + ) + + if total > budget_hard: + # We've stripped everything optional and we still overflow. + # MUST alone fits (we checked at the top), so this means our + # last-4 dialogue + must blocks together exceed hard. Fall back + # to the bare MUST core. + body = must_text + total = must_tokens + if total > budget_hard: + raise ValueError( + f"Prompt cannot fit budget_hard={budget_hard}; MUST core " + f"is {total} tokens" + ) + + return _emit(body, user_turn_prose) + + +def _emit(system_body: str, user_turn_prose: str | None) -> list[Message]: + msgs: list[Message] = [Message(role="system", content=system_body)] + if user_turn_prose is not None: + msgs.append(Message(role="user", content=user_turn_prose)) + return msgs + + +__all__ = ["assemble_narrative_prompt"] diff --git a/chat/services/regenerate.py b/chat/services/regenerate.py new file mode 100644 index 0000000..c92c0f0 --- /dev/null +++ b/chat/services/regenerate.py @@ -0,0 +1,285 @@ +"""Regenerate flow (T29). + +The user clicks "Regenerate" on the latest ``assistant_turn``. The UI +puts the prior ``user_turn`` into inline edit mode and submits to +:func:`regenerate_assistant_turn` either: + +- with **no edit** — we re-run the narrative against the original user + prose and append a fresh ``assistant_turn`` superseding the old one; +- with **edited prose** — we additionally append a ``user_turn_edit`` + event capturing the new prose, mark the original ``user_turn`` as + superseded by the edit, then run the narrative against the edited + prose. + +Per Requirements §10.2 superseded events are *kept in the log* — the +display layer hides them. This is what makes rewinding to before a +regenerate cheap: we just clear ``superseded_by`` on the old row. + +The supersede update is one of the rare "direct DB write" exceptions +documented in the plan: we manipulate metadata fields on the canonical +event_log row itself rather than projecting through a handler. + +Phase 1 simplifications (per the plan's "bound it" guidance): + +- Significance pass is *not* re-run on regenerate. The original score + remains attached to the prior memory. The state-update pass *is* re-run + so affinity/trust/knowledge reflect the new output. +- The route does not broadcast a fresh ``turn_html`` SSE event; T34 + polishes UI swaps. The user refreshes the page to see the new turn. +""" + +from __future__ import annotations + +import json +from sqlite3 import Connection + +from chat.config import Settings +from chat.eventlog.log import append_and_apply, append_event +from chat.services.memory_write import record_turn_memory +from chat.services.prompt import assemble_narrative_prompt +from chat.services.state_update import compute_state_update +from chat.state.edges import get_edge +from chat.state.entities import get_bot, get_you +from chat.state.world import active_scene, get_chat +from chat.web.pubsub import publish + + +async def regenerate_assistant_turn( + conn: Connection, + client, + *, + settings: Settings, + chat_id: str, + original_assistant_event_id: int, + edited_user_prose: str | None = None, +) -> str: + """Regenerate the assistant turn linked to ``original_assistant_event_id``. + + When ``edited_user_prose`` is provided the original user_turn is also + superseded by a fresh ``user_turn_edit`` event capturing the new + prose. Returns the new assistant text. + + Raises :class:`ValueError` when the chat or the assistant_turn event + cannot be found — the FastAPI route translates this to 404. + """ + chat = get_chat(conn, chat_id) + if chat is None: + raise ValueError("chat not found") + host_bot_id = chat["host_bot_id"] + host_bot = get_bot(conn, host_bot_id) or { + "id": host_bot_id, + "name": "bot", + "persona": "", + } + + # 1. Locate the original assistant_turn event. + row = conn.execute( + "SELECT payload_json FROM event_log " + "WHERE id = ? AND kind = 'assistant_turn'", + (original_assistant_event_id,), + ).fetchone() + if row is None: + raise ValueError("assistant_turn event not found") + original_assistant_payload = json.loads(row[0]) + original_user_turn_id = original_assistant_payload.get("user_turn_id") + + # 2. Determine the prose for the new prompt and (when edited) capture + # the user_turn_edit event up front so the new event ids exist before + # we link them from the assistant_turn payload. + new_user_event_id: int | None = None + if edited_user_prose is not None: + new_user_event_id = append_event( + conn, + kind="user_turn_edit", + payload={ + "chat_id": chat_id, + "prose": edited_user_prose, + "supersedes_user_turn_id": original_user_turn_id, + }, + ) + if original_user_turn_id is not None: + conn.execute( + "UPDATE event_log SET superseded_by = ? WHERE id = ?", + (new_user_event_id, original_user_turn_id), + ) + prose_for_prompt = edited_user_prose + else: + original_user_row = conn.execute( + "SELECT payload_json FROM event_log WHERE id = ?", + (original_user_turn_id,), + ).fetchone() if original_user_turn_id is not None else None + if original_user_row is not None: + prose_for_prompt = json.loads(original_user_row[0]).get("prose", "") + else: + prose_for_prompt = "" + + # 3. Build the recent-dialogue slice. Exclude the original + # assistant_turn explicitly (we haven't superseded it yet — that + # update lands at the end so the new event_id is known) and use the + # standard ``superseded_by IS NULL AND hidden = 0`` filter so any + # prior regenerates also drop out. + you_entity = get_you(conn) or {"name": "you", "persona": ""} + you_name = you_entity.get("name", "you") + cur = conn.execute( + "SELECT id, kind, payload_json FROM event_log " + "WHERE kind IN ('user_turn', 'user_turn_edit', 'assistant_turn') " + " AND id != ? " + " AND superseded_by IS NULL AND hidden = 0 " + "ORDER BY id DESC LIMIT 20", + (original_assistant_event_id,), + ) + rows = list(reversed(cur.fetchall())) + recent: list[dict] = [] + for _eid, kind, payload_json in rows: + p = json.loads(payload_json) + if p.get("chat_id") != chat_id: + continue + if kind in ("user_turn", "user_turn_edit"): + recent.append({"speaker": you_name, "text": p.get("prose", "")}) + else: + recent.append( + {"speaker": host_bot.get("name", "bot"), "text": p.get("text", "")} + ) + + # 4. Assemble the narrative prompt. ``recent`` already excludes the + # current user prose, which we pass through ``user_turn_prose``. + messages = assemble_narrative_prompt( + conn, + chat_id=chat_id, + speaker_bot_id=host_bot_id, + user_turn_prose=prose_for_prompt or None, + recent_dialogue=recent, + budget_soft=settings.narrative_budget_soft, + budget_hard=settings.narrative_budget_hard, + ) + + # 5. Stream the new narrative. + accumulated: list[str] = [] + async for chunk in client.stream( + messages, + model=settings.narrative_model, + max_tokens=settings.narrative_max_tokens, + temperature=settings.narrative_temperature, + ): + accumulated.append(chunk) + await publish( + chat_id, + {"event": "token", "text": chunk, "speaker_id": host_bot_id}, + ) + new_text = "".join(accumulated) + + # 6. Append the new assistant_turn event. ``user_turn_id`` points at + # the edit event when one was created, otherwise the original. The + # ``regenerated_from`` field is the back-pointer the UI uses for an + # "originally said …" affordance. + new_assistant_event_id = append_event( + conn, + kind="assistant_turn", + payload={ + "chat_id": chat_id, + "speaker_id": host_bot_id, + "text": new_text, + "truncated": False, + "user_turn_id": ( + new_user_event_id + if new_user_event_id is not None + else original_user_turn_id + ), + "regenerated_from": original_assistant_event_id, + }, + ) + + # 7. Mark the original assistant_turn as superseded by the new one. + conn.execute( + "UPDATE event_log SET superseded_by = ? WHERE id = ?", + (new_assistant_event_id, original_assistant_event_id), + ) + + # 8. Re-run downstream classifier passes (memory write + state update + # for both directed edges). Significance is intentionally skipped on + # regenerate (the prior score remains attached to the prior memory). + scene = active_scene(conn, chat_id) + record_turn_memory( + conn, + chat_id=chat_id, + host_bot_id=host_bot_id, + narrative_text=new_text, + scene_id=scene["id"] if scene else None, + chat_clock_at=chat.get("time"), + ) + + last_at = chat.get("time") + recent_for_update = recent + [ + {"speaker": host_bot.get("name", "bot"), "text": new_text} + ] + + edge_b2y = get_edge(conn, host_bot_id, "you") or { + "affinity": 50, + "trust": 50, + "summary": "", + } + update_b2y = await compute_state_update( + client, + model=settings.classifier_model, + source_id=host_bot_id, + target_id="you", + source_name=host_bot.get("name", "bot"), + source_persona=host_bot.get("persona", "") or "", + target_name=you_name, + prior_affinity=edge_b2y["affinity"], + prior_trust=edge_b2y["trust"], + prior_summary=edge_b2y.get("summary", "") or "", + recent_dialogue=recent_for_update, + ) + append_and_apply( + conn, + kind="edge_update", + payload={ + "source_id": host_bot_id, + "target_id": "you", + "chat_id": chat_id, + "affinity_delta": update_b2y.affinity_delta, + "trust_delta": update_b2y.trust_delta, + "knowledge_facts": update_b2y.knowledge_facts, + "last_interaction_at": last_at, + "last_interaction_chat_id": chat_id, + }, + ) + + edge_y2b = get_edge(conn, "you", host_bot_id) or { + "affinity": 50, + "trust": 50, + "summary": "", + } + update_y2b = await compute_state_update( + client, + model=settings.classifier_model, + source_id="you", + target_id=host_bot_id, + source_name=you_name, + source_persona=you_entity.get("persona", "") or "", + target_name=host_bot.get("name", "bot"), + prior_affinity=edge_y2b["affinity"], + prior_trust=edge_y2b["trust"], + prior_summary=edge_y2b.get("summary", "") or "", + recent_dialogue=recent_for_update, + ) + append_and_apply( + conn, + kind="edge_update", + payload={ + "source_id": "you", + "target_id": host_bot_id, + "chat_id": chat_id, + "affinity_delta": update_y2b.affinity_delta, + "trust_delta": update_y2b.trust_delta, + "knowledge_facts": update_y2b.knowledge_facts, + "last_interaction_at": last_at, + "last_interaction_chat_id": chat_id, + }, + ) + + return new_text + + +__all__ = ["regenerate_assistant_turn"] diff --git a/chat/services/reset.py b/chat/services/reset.py new file mode 100644 index 0000000..a8e573d --- /dev/null +++ b/chat/services/reset.py @@ -0,0 +1,23 @@ +from __future__ import annotations + +from sqlite3 import Connection + +from chat.eventlog.log import append_and_apply +from chat.state.entities import get_bot + + +def reset_bot(conn: Connection, bot_id: str, *, confirm_name: str) -> None: + """Reset a bot's runtime state via a ``bot_reset`` event. + + Validates that ``confirm_name`` matches the bot's stored ``name`` + exactly (case-sensitive, no trim). Raises: + + - ``ValueError("bot {bot_id} not found")`` when the bot is missing. + - ``ValueError("confirm_name does not match bot name")`` on mismatch. + """ + bot = get_bot(conn, bot_id) + if bot is None: + raise ValueError(f"bot {bot_id} not found") + if confirm_name != bot["name"]: + raise ValueError("confirm_name does not match bot name") + append_and_apply(conn, kind="bot_reset", payload={"bot_id": bot_id}) diff --git a/chat/services/rewind.py b/chat/services/rewind.py new file mode 100644 index 0000000..ed2e7b4 --- /dev/null +++ b/chat/services/rewind.py @@ -0,0 +1,112 @@ +"""Rewind service — truncate the event log past a chosen turn and re-project. + +Per Requirements §10.1 and Plan Task 28, "rewind to here" must: + +1. Take a snapshot of the current state so the user can recover (handed + off to :mod:`chat.services.snapshot`). +2. Truncate the event log past ``after_event_id`` — physical DELETE for + v1 simplicity; the spec says rewind should be a hard truncation, not + the soft ``hidden=1`` mechanism used by edits/regenerate. +3. Clear projected tables and re-project from the truncated log so live + state matches "what the world looked like at turn N". Without the + re-projection, projected tables would carry forward stale rows from + rewound events (e.g. an ``edge_update`` that bumped affinity past the + rewind point would still show in ``edges``). + +Re-projection is a full replay rather than a "revert delta" because most +projector handlers are idempotent inserts, but the edge handler is a +delta-shaped accumulator — there's no clean way to invert a single +``edge_update`` against ``edges.affinity`` without replay. Wiping + +replaying is straightforward and correct. +""" + +from __future__ import annotations + +from pathlib import Path +from sqlite3 import Connection + +from chat.db.connection import open_db +from chat.eventlog.projector import project +from chat.services.snapshot import take_snapshot + + +def compute_rewind_preview( + conn: Connection, after_event_id: int +) -> dict: + """Return counts of each event kind that would be removed by rewinding. + + Used by the preview modal so the user sees the impact (e.g. "this + will remove 8 events: 4 user_turn, 4 assistant_turn") before + confirming. Counts include hidden/superseded rows — they're still + physically deleted. + """ + cur = conn.execute( + "SELECT kind, COUNT(*) FROM event_log WHERE id > ? GROUP BY kind " + "ORDER BY kind", + (after_event_id,), + ) + counts = {kind: count for kind, count in cur.fetchall()} + total = sum(counts.values()) + return { + "after_event_id": after_event_id, + "total_events": total, + "by_kind": counts, + } + + +def execute_rewind( + *, db_path: Path, data_dir: Path, after_event_id: int +) -> Path: + """Take a snapshot, truncate, and re-project. Returns the snapshot path. + + The snapshot is taken inside the same connection scope as the + truncate + reproject so all three commit together — if any step + fails the connection's commit-on-exit is bypassed by the exception + and the database stays untouched. The snapshot file is on disk + regardless, which is the desired behaviour: even if the truncate + aborts, the user has a recovery point. + """ + with open_db(db_path) as conn: + # 1. Snapshot first — we want this on disk before any destructive + # operation runs. + snapshot_path = take_snapshot( + conn, data_dir=data_dir, kind="rewind" + ) + + # 2. Truncate the event log past the chosen id. Foreign keys are + # ON, but ``event_log.superseded_by`` self-references and the + # rows we're deleting are the only ones that could point + # forward — there's nothing to cascade. + conn.execute( + "DELETE FROM event_log WHERE id > ?", (after_event_id,) + ) + + # 3. Clear projected tables in topological order so FK ON DELETE + # constraints don't fire on referenced rows. ``activity`` and + # ``scenes`` reference ``containers``; ``chat_state`` references + # ``chats`` by id-convention only (no FK declared). ``memories``, + # ``edges``, ``bots``, ``you_entity``, and ``classifier_failures`` + # have no incoming FKs from other projected tables. + # + # ``executescript`` is intentionally avoided so foreign_keys=ON + # stays in effect for each statement — executescript would + # implicitly commit and reset some pragmas on certain SQLite + # builds. + conn.execute("DELETE FROM memories") + conn.execute("DELETE FROM activity") + conn.execute("DELETE FROM scenes") + conn.execute("DELETE FROM containers") + conn.execute("DELETE FROM chat_state") + conn.execute("DELETE FROM chats") + conn.execute("DELETE FROM edges") + conn.execute("DELETE FROM bots") + conn.execute("DELETE FROM you_entity") + conn.execute("DELETE FROM classifier_failures") + + # 4. Re-project from the truncated event log. Handler registry + # is module-level state populated by importing chat.state.* — + # callers (the route, tests) need to have those modules + # imported for this to do anything useful. + project(conn) + + return snapshot_path diff --git a/chat/services/scene_close.py b/chat/services/scene_close.py new file mode 100644 index 0000000..bfa049b --- /dev/null +++ b/chat/services/scene_close.py @@ -0,0 +1,100 @@ +"""Scene-close hard-signal detection (T26). + +A small classifier service that decides whether the user's prose narrates +a hard signal that should close the active scene. Hard signals (per +Requirements §7.2): + +* Container change parsed from prose ("we drove to the park", "we stepped + outside"). +* Explicit user pattern signaling end ("we're done here", "fade out", + "scene end"). + +NOT close signals: + +* Brief activity changes within the same container ("I sit down"). +* Future plans ("let's go to the park later"). + +The service returns a :class:`SceneCloseDecision`. The default on classifier +failure is ``should_close=False`` so the turn flow keeps moving — closing +on a misfire would be more disruptive than missing a real signal, and the +manual button in the drawer is always available as a fallback. + +Phase 2/3 will introduce automatic re-opening with the new container; for +T26 the close is one-way and the next user turn operates without an active +scene (the prompt assembler already tolerates this). +""" + +from __future__ import annotations + +from pydantic import BaseModel + +from chat.llm.classify import classify +from chat.llm.client import LLMClient + + +class SceneCloseDecision(BaseModel): + """Classifier verdict for scene-close detection. + + ``new_container_hint`` is captured opportunistically when the close + signal is a container change, but T26 doesn't act on it — Phase 2/3 + handles automatic re-opening at the new location. + """ + + should_close: bool = False + reason: str = "" + new_container_hint: str = "" + + +_SYSTEM = ( + "You decide whether a roleplay scene should close based on the user's " + "prose.\n" + "Close signals (return should_close=true):\n" + "- The prose narrates a CONTAINER CHANGE (moving to a different place, " + 'e.g. "we drove to the park", "we stepped outside").\n' + "- The prose has an EXPLICIT USER PATTERN signaling end " + '("we\'re done here", "fade out", "scene end").\n' + "\n" + "DO NOT close on:\n" + "- Brief activity changes within the same place " + '(e.g. "I sit down" — same room).\n' + "- Future plans " + '("let\'s go to the park later" — not yet).\n' + "\n" + 'Reply JSON: {"should_close": bool, "reason": str (short), ' + '"new_container_hint": str (optional name)}.' +) + + +async def detect_scene_close( + client: LLMClient, + *, + model: str, + prose: str, + current_container_name: str, + timeout_s: float = 10.0, +) -> SceneCloseDecision: + """Run the scene-close classifier on a single user turn. + + The current container name is passed in so the prompt can reason about + "different place" relative to the active scene rather than guessing. + On classifier failure (parse error twice), the returned decision is the + safe ``should_close=False`` default. + """ + user = ( + f"CURRENT CONTAINER: {current_container_name}\n" + f"\n" + f"PROSE:\n{prose}\n" + f"\n" + f"Decide whether to close the scene." + ) + return await classify( + client, + model=model, + system=_SYSTEM, + user=user, + schema=SceneCloseDecision, + default=SceneCloseDecision( + should_close=False, reason="fallback", new_container_hint="" + ), + timeout_s=timeout_s, + ) diff --git a/chat/services/scene_summarize.py b/chat/services/scene_summarize.py new file mode 100644 index 0000000..43fb5ec --- /dev/null +++ b/chat/services/scene_summarize.py @@ -0,0 +1,269 @@ +"""Per-POV scene summary and edge summary update on scene close (T27). + +When a scene closes — either auto-detected by the hard-signal classifier +in T26 or fired by the manual close button on the drawer — we run a +single-shot classifier per present witness that produces three signals +in one pass: + +* ``summary`` — a 2-4 sentence per-POV recap of the scene from this + witness's perspective. Different from omniscient narration; focuses on + what the witness noticed/felt/remembers. +* ``knowledge_facts`` — concrete new things this witness learned about + the user during the scene. Promoted to the directed edge's + ``knowledge`` list via ``edge_update``. +* ``relationship_summary`` — a 1-2 sentence delta on how the + witness's relationship to the user shifted in this scene. v1 + combines this with the prior edge summary by simple concatenation — + the LLM is asked to phrase ``relationship_summary`` as a merge-ready + fragment, so the result reads naturally without a second classifier + round-trip. + +Phase 1 single-bot only the host bot is summarized; "you" doesn't have +a memory store in v1 so per-POV writes for the user are deferred. The +:func:`apply_scene_close_summary` driver is intentionally tolerant: if +no memories belong to the closed scene it silently skips the rewrite, +and a flapping classifier returns the empty default so the close flow +keeps moving. +""" + +from __future__ import annotations + +import json +from sqlite3 import Connection + +from pydantic import BaseModel, Field + +from chat.eventlog.log import append_and_apply +from chat.llm.classify import classify +from chat.llm.client import LLMClient + + +class ScenePOVSummary(BaseModel): + """Classifier output: one witness's view of a closing scene. + + Defaults are an inert no-op so a classifier failure is harmless — + callers can apply the result unconditionally and end up not + rewriting anything when the model misbehaves. + """ + + summary: str = "" + knowledge_facts: list[str] = Field(default_factory=list) + relationship_summary: str = "" + + +_SYSTEM_TEMPLATE = ( + "You are summarizing a roleplay scene from {bot_name}'s point of " + "view. Read the dialogue, then output JSON with exactly three " + "fields:\n" + "- summary: 2-4 sentences, in {bot_name}'s POV, of what happened " + "in the scene. This is NOT omniscient narration — focus on what " + "{bot_name} noticed, felt, and would remember.\n" + "- knowledge_facts: list of NEW factual things {bot_name} learned " + "about the user during this scene. Use specific stated content; do " + "not infer or interpret. Empty list is fine.\n" + "- relationship_summary: a SHORT (1-2 sentence) summary of how " + "{bot_name}'s relationship with the user changed or developed in " + "this scene. Phrase it so it reads as a continuation of the prior " + "summary; the caller will concatenate them.\n\n" + "Be specific. Avoid generic phrases." +) + + +def _format_dialogue(dialogue: list[dict]) -> str: + if not dialogue: + return "(no dialogue)" + return "\n".join( + f"{turn.get('speaker', '?')}: {turn.get('text', '')}" + for turn in dialogue + ) + + +async def summarize_scene( + client: LLMClient, + *, + model: str, + bot_name: str, + bot_persona: str, + you_name: str, + prior_edge_summary: str, + dialogue: list[dict], + timeout_s: float = 10.0, +) -> ScenePOVSummary: + """Run the per-POV summary classifier for one witness. + + The signature mirrors :func:`compute_state_update` — passing the + bot's name and persona as separate fields lets the prompt address + the model directly ("YOU are {bot_name}") rather than handing it an + opaque id. ``prior_edge_summary`` is included so the classifier can + phrase ``relationship_summary`` as an additive fragment. + + Returns the empty default on classifier failure (after one retry) + rather than raising, so the close pipeline keeps moving. + """ + system = _SYSTEM_TEMPLATE.format(bot_name=bot_name) + user = ( + f"YOU are {bot_name}. {bot_persona or '(no persona on file)'}\n" + f"USER name: {you_name}\n" + f"PRIOR EDGE SUMMARY ({bot_name} -> {you_name}): " + f"{prior_edge_summary or '(empty)'}\n\n" + f"DIALOGUE:\n{_format_dialogue(dialogue)}\n\n" + f"Produce the JSON summary in {bot_name}'s POV." + ) + return await classify( + client, + model=model, + system=system, + user=user, + schema=ScenePOVSummary, + default=ScenePOVSummary(), + timeout_s=timeout_s, + ) + + +def _read_recent_dialogue( + conn: Connection, chat_id: str, *, limit: int = 50 +) -> list[dict]: + """Pull the last ``limit`` user/assistant turns for ``chat_id``. + + Phase 1 ``user_turn`` / ``assistant_turn`` events don't carry a + ``scene_id``, so we approximate the scene's transcript by taking + the most recent turns of the chat. Superseded and hidden rows are + filtered out so regenerated turns (T29) don't bleed into the + summary. + """ + cur = conn.execute( + "SELECT kind, payload_json FROM event_log " + "WHERE kind IN ('user_turn', 'assistant_turn') " + " AND superseded_by IS NULL AND hidden = 0 " + "ORDER BY id DESC LIMIT ?", + (limit,), + ) + rows = list(reversed(cur.fetchall())) + out: list[dict] = [] + for kind, payload_json in rows: + p = json.loads(payload_json) + if p.get("chat_id") != chat_id: + continue + if kind == "user_turn": + out.append({"speaker": "you", "text": p.get("prose", "")}) + else: + out.append( + { + "speaker": p.get("speaker_id", "bot"), + "text": p.get("text", ""), + } + ) + return out + + +async def apply_scene_close_summary( + conn: Connection, + client: LLMClient, + *, + classifier_model: str, + chat_id: str, + scene_id: int, + host_bot_id: str, + timeout_s: float = 10.0, +) -> ScenePOVSummary: + """Drive the per-POV summary pipeline after ``scene_closed``. + + Steps (Phase 1, single-bot): + 1. Gather the closing scene's dialogue from the event_log. + 2. Run :func:`summarize_scene` for the host bot. + 3. Rewrite each scene-bound memory's ``pov_summary`` via + ``manual_edit`` (target_kind ``memory_pov_summary``), capturing + the prior value for §6.4 reversibility. + 4. Update the bot->you edge summary via ``manual_edit`` with the + new ``edge_summary`` target_kind. v1 combines prior + new by + concatenation — the classifier's ``relationship_summary`` is + already phrased as a continuation. + 5. Append any new knowledge_facts to the same edge via + ``edge_update``. + + Tolerant of missing pieces: no memories -> skip step 3 silently; + no edge row -> skip step 4; empty knowledge_facts -> skip step 5. + The classifier's empty default flows through harmlessly. + """ + # Local imports to keep the module-level surface tight and avoid + # any chance of a circular dep through chat.state.*. + from chat.state.edges import get_edge + from chat.state.entities import get_bot, get_you + + host_bot = get_bot(conn, host_bot_id) or {"name": host_bot_id, "persona": ""} + you_entity = get_you(conn) or {"name": "you", "persona": ""} + + dialogue = _read_recent_dialogue(conn, chat_id) + + edge_b2y = get_edge(conn, host_bot_id, "you") + prior_summary = (edge_b2y or {}).get("summary", "") or "" + + pov = await summarize_scene( + client, + model=classifier_model, + bot_name=host_bot.get("name", host_bot_id), + bot_persona=host_bot.get("persona", "") or "", + you_name=you_entity.get("name", "you") or "you", + prior_edge_summary=prior_summary, + dialogue=dialogue, + timeout_s=timeout_s, + ) + + # Update memories belonging to the closed scene for the host bot. + cur = conn.execute( + "SELECT id, pov_summary FROM memories " + "WHERE scene_id = ? AND owner_id = ?", + (scene_id, host_bot_id), + ) + for memory_id, prior_pov in cur.fetchall(): + if not pov.summary: + # Empty default -> skip the memory rewrite; the seeded + # per-turn pov_summary stays in place. + continue + append_and_apply( + conn, + kind="manual_edit", + payload={ + "target_kind": "memory_pov_summary", + "target_id": int(memory_id), + "prior_value": prior_pov, + "new_value": pov.summary, + }, + ) + + # Update the bot->you edge summary if we have an edge row and a + # non-empty relationship_summary to merge. + if edge_b2y is not None and pov.relationship_summary: + new_summary = ( + f"{prior_summary} {pov.relationship_summary}".strip() + if prior_summary + else pov.relationship_summary + ) + append_and_apply( + conn, + kind="manual_edit", + payload={ + "target_kind": "edge_summary", + "target_id": { + "source_id": host_bot_id, + "target_id": "you", + }, + "prior_value": prior_summary, + "new_value": new_summary, + }, + ) + + # Append knowledge_facts to the bot->you edge if present. + if pov.knowledge_facts: + append_and_apply( + conn, + kind="edge_update", + payload={ + "source_id": host_bot_id, + "target_id": "you", + "chat_id": chat_id, + "knowledge_facts": list(pov.knowledge_facts), + }, + ) + + return pov diff --git a/chat/services/significance.py b/chat/services/significance.py new file mode 100644 index 0000000..eb3791c --- /dev/null +++ b/chat/services/significance.py @@ -0,0 +1,75 @@ +"""Turn-level significance scorer (T22). + +Per Requirements §11.1, each turn is scored on a 0-3 scale: + +- 0 = Routine: small talk, ordinary action. +- 1 = Notable: a specific detail or beat worth remembering. +- 2 = Significant: a scene-level moment, real disagreement, confided secret. +- 3 = Pivotal: a relationship-altering event (first kiss, betrayal, "I love + you"). + +The scorer is conservative: pivotal (3) requires a clear signal because the +auto-pin rule (§8.5) gives those memories permanent shelf space. The +classifier returns a strict-JSON ``SignificanceVerdict``; a malformed or +refusal-shaped response falls back to ``score=1`` (Notable) — a safe +middle-of-the-road default that won't trigger auto-pin. +""" + +from __future__ import annotations + +from pydantic import BaseModel, Field + +from chat.llm.classify import classify +from chat.llm.client import LLMClient + + +class SignificanceVerdict(BaseModel): + score: int = Field(ge=0, le=3) + reason: str = "" + + +_SYSTEM = """You score the significance of a roleplay turn 0-3: +0 = Routine: small talk, ordinary action. +1 = Notable: a specific detail or beat worth remembering. +2 = Significant: a scene-level moment, real disagreement, confided secret. +3 = Pivotal: a relationship-altering event (first kiss, betrayal, "I love you"). + +Be conservative — pivotal (3) requires a clear signal. Reply with JSON: {"score": int 0-3, "reason": str}.""" + + +async def compute_significance( + client: LLMClient, + *, + model: str, + narrative_text: str, + prior_dialogue: list[dict], + timeout_s: float = 10.0, +) -> int: + """Score the significance of ``narrative_text`` (the just-written turn). + + ``prior_dialogue`` is a list of ``{"speaker", "text"}`` dicts ordered + oldest-first; the last 6 entries are stitched into the user prompt as + context so the classifier can recognize escalation. Returns an int in + ``[0, 3]`` — clamped defensively in case the classifier slips a value + past the schema validator. + """ + user_prompt = "PRIOR DIALOGUE:\n" + for turn in prior_dialogue[-6:]: + speaker = turn.get("speaker", "?") + text = turn.get("text", "") + user_prompt += f"{speaker}: {text}\n" + user_prompt += ( + f"\nNEW TURN:\n{narrative_text}\n\n" + "Score the significance of the NEW TURN." + ) + + result = await classify( + client, + model=model, + system=_SYSTEM, + user=user_prompt, + schema=SignificanceVerdict, + default=SignificanceVerdict(score=1, reason="fallback"), + timeout_s=timeout_s, + ) + return max(0, min(3, result.score)) diff --git a/chat/services/snapshot.py b/chat/services/snapshot.py new file mode 100644 index 0000000..e1679b8 --- /dev/null +++ b/chat/services/snapshot.py @@ -0,0 +1,245 @@ +"""Snapshot service — write a JSON dump of all projected tables to disk. + +Two snapshot kinds, both covered by this module: + +* ``rewind`` (T28, Requirements §10.1): pre-rewind safety snapshot so the + user can recover if a rewind was a mistake. Retention: 14 days. +* ``periodic`` (T31, Requirements §10.4): full-state checkpoint taken + every 100 events OR every 30 minutes since the last one. Retention: + the most recent 5 are kept; older ones are pruned on write. + +Both kinds live under ``data/snapshots/{kind}/`` with a UTC timestamp +filename so chronological listing matches creation order. + +The dump captures the event log (so the original event sequence is +preserved verbatim), every projected table, and a top-level +``last_event_id`` recording the highest ``event_log.id`` at snapshot +time. The ``last_event_id`` is what the cold-load fast-path uses to +replay only events past the snapshot rather than the entire log. + +The FTS shadow table ``memories_fts`` is intentionally skipped — it's a +virtual table maintained by the ``memories_ai/au/ad`` triggers, so it +rebuilds itself on a memories re-load. Snapshotting it would also fail +``PRAGMA table_info`` cleanly since FTS5 reports its columns differently. +""" + +from __future__ import annotations + +import json +import time +from datetime import datetime, timezone +from pathlib import Path +from sqlite3 import Connection + +# Periodic snapshot triggers (Requirements §10.4): "every 100 events OR +# every 30 minutes since last snapshot". Module-level so tests can read +# them and so the values stay together with the policy that uses them. +EVENT_COUNT_THRESHOLD = 100 +TIME_THRESHOLD_SECONDS = 30 * 60 # 30 minutes + +# Order doesn't affect correctness for snapshotting (we read, not write), +# but listing tables explicitly keeps the snapshot stable across schema +# evolution: a new table won't silently change the dump shape until it's +# added here. +PROJECTED_TABLES = [ + "bots", + "you_entity", + "edges", + "memories", + "memories_fts", + "chats", + "chat_state", + "containers", + "scenes", + "activity", + "classifier_failures", +] + + +def take_snapshot( + conn: Connection, *, data_dir: Path, kind: str = "rewind" +) -> Path: + """Write a JSON dump of the event log and projected tables. + + Returns the path to the written snapshot file. Creates parent + directories as needed. Filename is a UTC timestamp in + ``YYYYMMDDTHHMMSSZ`` form so chronological listing matches creation + order. + + The dump's top-level ``last_event_id`` is the highest ``event_log.id`` + at snapshot time (0 if the log is empty). This is what the cold-load + fast-path uses to know which suffix of the log to replay. + """ + snapshot_dir = data_dir / "snapshots" / kind + snapshot_dir.mkdir(parents=True, exist_ok=True) + timestamp = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ") + path = snapshot_dir / f"{timestamp}.json" + + dump: dict = {} + + # Record the high-water-mark id up front so cold-load can replay + # only events past it. ``MAX(id)`` is None on an empty log; treat + # that as 0 (i.e. "replay everything"). + cur = conn.execute("SELECT MAX(id) FROM event_log") + max_id_row = cur.fetchone() + dump["last_event_id"] = max_id_row[0] if max_id_row[0] is not None else 0 + + # Event log: pull every column we care about. ``ts`` and the + # superseded/hidden flags are needed to faithfully reconstruct the + # log on restore. + cur = conn.execute( + "SELECT id, branch_id, ts, kind, payload_json, superseded_by, hidden " + "FROM event_log ORDER BY id" + ) + dump["event_log"] = [ + { + "id": r[0], + "branch_id": r[1], + "ts": r[2], + "kind": r[3], + "payload_json": r[4], + "superseded_by": r[5], + "hidden": r[6], + } + for r in cur.fetchall() + ] + + for table in PROJECTED_TABLES: + if table == "memories_fts": + # Virtual FTS5 table — rebuilt by triggers on insert, no need + # to snapshot it (and ``PRAGMA table_info`` reports its + # columns differently). + continue + cur = conn.execute(f"PRAGMA table_info({table})") + cols = [c[1] for c in cur.fetchall()] + if not cols: + # Table not present in this schema version — leave an empty + # list rather than raising, so older snapshots can survive. + dump[table] = [] + continue + cur = conn.execute(f"SELECT {', '.join(cols)} FROM {table}") + dump[table] = [dict(zip(cols, row)) for row in cur.fetchall()] + + # ``default=str`` covers Path-like or datetime values that might + # sneak through if a column ever stored them; the projected tables + # all use TEXT so this is mostly defensive. + path.write_text(json.dumps(dump, default=str)) + return path + + +def latest_snapshot_path(data_dir: Path, kind: str = "periodic") -> Path | None: + """Return the most recent snapshot file for ``kind``, or None if none exist. + + Sorting by filename works because :func:`take_snapshot` uses a UTC + timestamp in ``YYYYMMDDTHHMMSSZ`` form — lexicographic order matches + chronological order. + """ + snapshot_dir = data_dir / "snapshots" / kind + if not snapshot_dir.exists(): + return None + files = sorted(snapshot_dir.glob("*.json")) + return files[-1] if files else None + + +def should_take_periodic_snapshot( + conn: Connection, data_dir: Path +) -> bool: + """Decide whether a periodic snapshot is due per Requirements §10.4. + + The policy: + + * No prior snapshot and at least one event in the log → take one. + * Time since last snapshot ≥ ``TIME_THRESHOLD_SECONDS`` → take one. + * New events since last snapshot's ``last_event_id`` ≥ + ``EVENT_COUNT_THRESHOLD`` → take one. + + "Time since last snapshot" is measured by the file's mtime — we + don't trust the timestamp embedded in the filename for clock drift + reasons. + """ + latest = latest_snapshot_path(data_dir, kind="periodic") + if latest is None: + # No prior snapshot; take one if there are any events to capture. + cur = conn.execute("SELECT COUNT(*) FROM event_log") + return cur.fetchone()[0] > 0 + + age_seconds = time.time() - latest.stat().st_mtime + if age_seconds >= TIME_THRESHOLD_SECONDS: + return True + + # Count events appended since the last snapshot was written. Reading + # ``last_event_id`` from the dump is cheap (a few KB at most for the + # header) but we still avoid loading the full file by parsing once. + last_dump = json.loads(latest.read_text()) + last_event_id = last_dump.get("last_event_id", 0) + cur = conn.execute( + "SELECT COUNT(*) FROM event_log WHERE id > ?", (last_event_id,) + ) + new_event_count = cur.fetchone()[0] + return new_event_count >= EVENT_COUNT_THRESHOLD + + +def prune_periodic_snapshots(data_dir: Path, keep: int = 5) -> int: + """Delete all but the most recent ``keep`` periodic snapshots. + + Returns the number of files removed. Safe to call when the directory + doesn't exist (returns 0). Sorting is by filename, which is the UTC + timestamp — same ordering :func:`latest_snapshot_path` uses. + """ + snapshot_dir = data_dir / "snapshots" / "periodic" + if not snapshot_dir.exists(): + return 0 + files = sorted(snapshot_dir.glob("*.json")) + to_remove = files[:-keep] if len(files) > keep else [] + for f in to_remove: + f.unlink() + return len(to_remove) + + +def restore_from_snapshot(conn: Connection, snapshot_path: Path) -> int: + """Restore projected tables from ``snapshot_path``. + + Returns the snapshot's ``last_event_id`` so callers (the cold-load + fast-path in :func:`chat.app.lifespan`) know what suffix of the + event log still needs replaying. + + Projected tables are cleared in the same FK-respecting order as + :func:`chat.services.rewind.execute_rewind`, then re-populated from + the dump. ``memories_fts`` is skipped — it's a virtual FTS5 table + that rebuilds itself when rows hit ``memories``. The event log + itself is *not* touched: cold-load assumes the on-disk log is the + source of truth and the snapshot is just a fast-forward to skip + re-projecting old events. + """ + dump = json.loads(snapshot_path.read_text()) + + # Same delete order as rewind: child tables before parents so FK + # ON DELETE doesn't fire on referenced rows. + conn.execute("DELETE FROM memories") + conn.execute("DELETE FROM activity") + conn.execute("DELETE FROM scenes") + conn.execute("DELETE FROM containers") + conn.execute("DELETE FROM chat_state") + conn.execute("DELETE FROM chats") + conn.execute("DELETE FROM edges") + conn.execute("DELETE FROM bots") + conn.execute("DELETE FROM you_entity") + conn.execute("DELETE FROM classifier_failures") + + for table in PROJECTED_TABLES: + if table == "memories_fts": + # Rebuilt by triggers when memories rows are inserted below. + continue + rows = dump.get(table, []) + if not rows: + continue + cols = list(rows[0].keys()) + placeholders = ", ".join("?" * len(cols)) + col_list = ", ".join(cols) + for row in rows: + conn.execute( + f"INSERT INTO {table} ({col_list}) VALUES ({placeholders})", + tuple(row[c] for c in cols), + ) + + return dump.get("last_event_id", 0) diff --git a/chat/services/state_update.py b/chat/services/state_update.py new file mode 100644 index 0000000..c9408fc --- /dev/null +++ b/chat/services/state_update.py @@ -0,0 +1,144 @@ +"""Post-turn state-update pass. + +Per Requirements §3.4, after every utterance we run a classifier on each +present entity (silent witnesses included) to extract directed-edge +deltas — what changed in *source*'s view of *target*. The classifier +returns three signals: + +- ``affinity_delta`` — signed change in how warmly source feels (typical + range -3..+3; the edge handler clamps the running total to 0..100). +- ``trust_delta`` — signed change in source's trust of target (same + shape). +- ``knowledge_facts`` — concrete things source learned about target + during this exchange. Stored verbatim and appended to ``edge.knowledge``. + +The wrapper deliberately uses :func:`chat.llm.classify.classify` with a +``default=StateUpdate()`` so a flapping classifier never blocks the turn +flow — at worst the edge sits unchanged and the next turn tries again +(§3.3 "graceful degradation" rule). +""" + +from __future__ import annotations + +from pydantic import BaseModel, Field + +from chat.llm.classify import classify +from chat.llm.client import LLMClient + + +class StateUpdate(BaseModel): + """One directed-edge update from a single classifier call. + + Defaults are deliberately a no-op (zero deltas, empty facts) so a + failing classifier produces a benign event rather than a disruption. + """ + + affinity_delta: int = 0 + trust_delta: int = 0 + knowledge_facts: list[str] = Field(default_factory=list) + + +_SYSTEM_PROMPT = ( + "You are reading a recent slice of dialogue from a roleplay scene. " + "You assess how SOURCE's view of TARGET shifted based on what was " + "said — including silent witnessing (SOURCE may not have spoken).\n\n" + "Output a JSON object with exactly three fields:\n" + "- affinity_delta: signed integer in [-3, 3]. How much warmer " + "(positive) or cooler (negative) SOURCE now feels toward TARGET.\n" + "- trust_delta: signed integer in [-3, 3]. How much more (positive) " + "or less (negative) SOURCE now trusts TARGET.\n" + "- knowledge_facts: list of short strings. New, concrete facts " + "SOURCE learned about TARGET in this exchange. Use TARGET's actual " + "stated content; do not infer or interpret. Empty list is fine.\n\n" + "Be conservative. Most turns produce small deltas (-1, 0, +1). " + "Reserve +/-2 or +/-3 for moments that materially shift the " + "relationship. Knowledge_facts should be specific things stated in " + "dialogue (e.g. \"works at the bakery\"), not interpretations " + "(\"seems lonely\")." +) + + +def _format_dialogue(recent_dialogue: list[dict]) -> str: + """Render the recent-dialogue slice as plain ``Speaker: text`` lines.""" + if not recent_dialogue: + return "(no dialogue yet)" + lines = [] + for turn in recent_dialogue: + speaker = turn.get("speaker", "?") + text = turn.get("text", "") + lines.append(f"{speaker}: {text}") + return "\n".join(lines) + + +def _build_user_prompt( + *, + source_name: str, + source_persona: str, + target_name: str, + prior_affinity: int, + prior_trust: int, + prior_summary: str, + recent_dialogue: list[dict], +) -> str: + return ( + f"SOURCE: {source_name}\n" + f"SOURCE_PERSONA: {source_persona or '(none)'}\n" + f"TARGET: {target_name}\n" + f"PRIOR_AFFINITY (0-100): {prior_affinity}\n" + f"PRIOR_TRUST (0-100): {prior_trust}\n" + f"PRIOR_SUMMARY: {prior_summary or '(none)'}\n\n" + f"RECENT_DIALOGUE:\n{_format_dialogue(recent_dialogue)}\n\n" + "How did SOURCE's view of TARGET shift? Respond with JSON only." + ) + + +async def compute_state_update( + client: LLMClient, + *, + model: str, + source_id: str, + target_id: str, + source_name: str, + source_persona: str, + target_name: str, + prior_affinity: int, + prior_trust: int, + prior_summary: str, + recent_dialogue: list[dict], + timeout_s: float = 10.0, +) -> StateUpdate: + """Run a classifier pass and return the directed-edge update. + + On classifier failure (after retry) returns the schema default — a + no-op ``StateUpdate`` — so the turn flow can keep moving. The + ``source_id`` / ``target_id`` arguments are accepted for symmetry + with the caller (T20's POST flow uses them when emitting the + ``edge_update`` event); they're not currently embedded in the + prompt because the classifier reasons about names, not opaque ids. + """ + # ``source_id``/``target_id`` are kept on the signature even though + # the prompt only quotes the names: callers in turns.py thread the + # ids straight from this function's args into the appended event. + del source_id, target_id # silence unused-arg lint cleanly + + user_prompt = _build_user_prompt( + source_name=source_name, + source_persona=source_persona, + target_name=target_name, + prior_affinity=prior_affinity, + prior_trust=prior_trust, + prior_summary=prior_summary, + recent_dialogue=recent_dialogue, + ) + + return await classify( + client, + model=model, + system=_SYSTEM_PROMPT, + user=user_prompt, + schema=StateUpdate, + default=StateUpdate(), + timeout_s=timeout_s, + ) + + diff --git a/chat/services/turn_parse.py b/chat/services/turn_parse.py new file mode 100644 index 0000000..df721dc --- /dev/null +++ b/chat/services/turn_parse.py @@ -0,0 +1,94 @@ +"""Turn input parser. + +Service-layer function that splits a user's authored turn into typed +segments — ``dialogue``, ``action``, or ``ooc`` (out-of-character). + +Per Requirements §6.1 a turn is mixed prose with three conventions: + +- ``*action*`` (single asterisks around prose) → action segment. +- Quoted text, or bare prose between the conventions → dialogue. +- ``((double parens))`` → OOC, the author talking to the system rather + than the bot. Downstream (T19) strips OOC from the prompt sent to the + bot but keeps it in the transcript display. + +A regex-based splitter would brittle on edge cases (unclosed asterisks, +nested quotes, mixed punctuation), so v1 delegates the segmentation to +the classifier. The configurable ``Settings.ooc_marker`` is *not* read +here: the classifier figures OOC out from ``((`` ``))`` regardless of +config-time choice; marker-based stripping is a downstream concern. +""" + +from __future__ import annotations + +from pydantic import BaseModel + +from chat.llm.classify import classify +from chat.llm.client import LLMClient + + +class TurnSegment(BaseModel): + """One classified piece of a turn. + + ``kind`` is kept as a plain ``str`` (not a ``Literal``) so an + unexpected classifier output doesn't crash parsing — callers that + care about specific values can check defensively. + """ + + kind: str # "dialogue" | "action" | "ooc" + text: str + + +class ParsedTurn(BaseModel): + """A turn split into ordered, typed segments.""" + + segments: list[TurnSegment] + + +_SYSTEM_PROMPT = ( + "You are splitting a roleplay turn into typed segments. The input " + "is mixed prose with three conventions:\n" + "- *text in single asterisks* is an ACTION segment.\n" + "- \"quoted text\" or bare prose between conventions is a DIALOGUE segment.\n" + "- ((text in double parens)) is an OOC (out-of-character) segment — " + "the author talking to the system, not the in-fiction bot.\n\n" + "Output a JSON object with shape " + '{"segments": [{"kind": "...", "text": "..."}, ...]} ' + "where each ``kind`` is exactly one of: dialogue, action, ooc. " + "Preserve the original substring text as ``text``: do not rewrite, " + "translate, or normalize punctuation — strip only the marker " + "characters (asterisks, surrounding quotes, double parens) so " + "``text`` is the inner content. Emit segments in the order they " + "appear in the input." +) + + +async def parse_turn( + client: LLMClient, + *, + model: str, + prose: str, + timeout_s: float = 10.0, +) -> ParsedTurn: + """Parse a user turn into typed segments. + + Calls :func:`chat.llm.classify.classify` under the hood. Empty or + whitespace-only prose short-circuits to an empty ``ParsedTurn`` + without an LLM call (the classifier would error on empty input + anyway, and the result is unambiguous). + + Raises ``RuntimeError`` if the classifier fails twice — no default + is supplied, since the caller (T19's turn flow) is responsible for + surfacing the error to the user. + """ + if not prose.strip(): + return ParsedTurn(segments=[]) + + user_prompt = f"INPUT:\n{prose}" + return await classify( + client, + model=model, + system=_SYSTEM_PROMPT, + user=user_prompt, + schema=ParsedTurn, + timeout_s=timeout_s, + ) diff --git a/chat/state/__init__.py b/chat/state/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/chat/state/edges.py b/chat/state/edges.py new file mode 100644 index 0000000..03be66b --- /dev/null +++ b/chat/state/edges.py @@ -0,0 +1,84 @@ +from __future__ import annotations +import json +from sqlite3 import Connection +from chat.eventlog.projector import on +from chat.eventlog.log import Event + + +def _clamp(value: int, lo: int = 0, hi: int = 100) -> int: + return max(lo, min(hi, value)) + + +@on("edge_update") +def _apply_edge_update(conn: Connection, e: Event) -> None: + p = e.payload + source_id = p["source_id"] + target_id = p["target_id"] + chat_id = p.get("chat_id") + + # Upsert: ensure a row exists with defaults, then apply deltas. + conn.execute( + "INSERT OR IGNORE INTO edges (chat_id, source_id, target_id) VALUES (?, ?, ?)", + (chat_id, source_id, target_id), + ) + + row = conn.execute( + "SELECT affinity, trust, knowledge_json, last_interaction_chat_id, last_interaction_at " + "FROM edges WHERE source_id = ? AND target_id = ?", + (source_id, target_id), + ).fetchone() + affinity, trust, knowledge_json, last_chat_id, last_at = row + + affinity_delta = int(p.get("affinity_delta", 0)) + trust_delta = int(p.get("trust_delta", 0)) + new_affinity = _clamp(affinity + affinity_delta) + new_trust = _clamp(trust + trust_delta) + + new_facts = p.get("knowledge_facts") or [] + if new_facts: + knowledge = json.loads(knowledge_json) + knowledge.extend(new_facts) + knowledge_json = json.dumps(knowledge) + + payload_at = p.get("last_interaction_at") + payload_chat_id = p.get("last_interaction_chat_id") + if payload_at is not None: + last_at = payload_at + if payload_chat_id is not None: + last_chat_id = payload_chat_id + + conn.execute( + "UPDATE edges SET affinity = ?, trust = ?, knowledge_json = ?, " + "last_interaction_chat_id = ?, last_interaction_at = ? " + "WHERE source_id = ? AND target_id = ?", + (new_affinity, new_trust, knowledge_json, last_chat_id, last_at, + source_id, target_id), + ) + + +def get_edge(conn: Connection, source_id: str, target_id: str) -> dict | None: + row = conn.execute( + "SELECT * FROM edges WHERE source_id = ? AND target_id = ?", + (source_id, target_id), + ).fetchone() + if not row: + return None + cols = [c[1] for c in conn.execute("PRAGMA table_info(edges)").fetchall()] + d = dict(zip(cols, row)) + d["knowledge"] = json.loads(d.pop("knowledge_json")) + return d + + +def list_edges_for(conn: Connection, source_id: str) -> list[dict]: + cur = conn.execute( + "SELECT * FROM edges WHERE source_id = ? ORDER BY target_id", + (source_id,), + ) + rows = cur.fetchall() + cols = [c[1] for c in conn.execute("PRAGMA table_info(edges)").fetchall()] + out: list[dict] = [] + for row in rows: + d = dict(zip(cols, row)) + d["knowledge"] = json.loads(d.pop("knowledge_json")) + out.append(d) + return out diff --git a/chat/state/entities.py b/chat/state/entities.py new file mode 100644 index 0000000..df14565 --- /dev/null +++ b/chat/state/entities.py @@ -0,0 +1,94 @@ +from __future__ import annotations +import json +from sqlite3 import Connection +from chat.eventlog.projector import on +from chat.eventlog.log import Event + + +@on("bot_authored") +def _apply_bot_authored(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "INSERT OR REPLACE INTO bots " + "(id, name, persona, voice_samples_json, traits_json, backstory, " + " initial_relationship_to_you, kickoff_prose) " + "VALUES (?, ?, ?, ?, ?, ?, ?, ?)", + (p["id"], p["name"], p["persona"], + json.dumps(p.get("voice_samples", [])), + json.dumps(p.get("traits", [])), + p.get("backstory", ""), + p.get("initial_relationship_to_you", ""), + p.get("kickoff_prose", "")), + ) + + +@on("you_authored") +def _apply_you_authored(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "INSERT OR REPLACE INTO you_entity (id, name, pronouns, persona) VALUES (1, ?, ?, ?)", + (p["name"], p.get("pronouns", ""), p.get("persona", "")), + ) + + +@on("bot_reset") +def _apply_bot_reset(conn: Connection, e: Event) -> None: + """Purge per-bot runtime state while preserving the bot's identity row. + + Wipes chats hosted by this bot (with cascading chat-scoped tables), + memories owned by this bot, edges involving this bot, and the bot's own + activity row. The ``bots`` row itself is preserved so identity, + initial-relationship, and kickoff prose remain authored. + """ + bot_id = e.payload["bot_id"] + + chat_ids = [ + row[0] + for row in conn.execute( + "SELECT id FROM chats WHERE host_bot_id = ?", (bot_id,) + ).fetchall() + ] + for chat_id in chat_ids: + conn.execute("DELETE FROM scenes WHERE chat_id = ?", (chat_id,)) + conn.execute("DELETE FROM containers WHERE chat_id = ?", (chat_id,)) + conn.execute("DELETE FROM chat_state WHERE chat_id = ?", (chat_id,)) + conn.execute("DELETE FROM chats WHERE id = ?", (chat_id,)) + + # Activity for this bot's entity row (independent of chat_id since the + # ``activity`` table is keyed on entity_id). + conn.execute("DELETE FROM activity WHERE entity_id = ?", (bot_id,)) + + # Memories authored by this bot. + conn.execute("DELETE FROM memories WHERE owner_id = ?", (bot_id,)) + + # Edges in either direction involving this bot. + conn.execute( + "DELETE FROM edges WHERE source_id = ? OR target_id = ?", + (bot_id, bot_id), + ) + # NOTE: bots row itself is preserved (identity, kickoff_prose intact). + # NOTE: "you" activity (entity_id="you") may linger from a deleted chat; + # acceptable for v1 — Phase 1.5 cleanup if needed. + + +def get_bot(conn: Connection, bot_id: str) -> dict | None: + row = conn.execute("SELECT * FROM bots WHERE id = ?", (bot_id,)).fetchone() + if not row: + return None + cols = [c[1] for c in conn.execute("PRAGMA table_info(bots)").fetchall()] + d = dict(zip(cols, row)) + d["voice_samples"] = json.loads(d.pop("voice_samples_json")) + d["traits"] = json.loads(d.pop("traits_json")) + return d + + +def list_bots(conn: Connection) -> list[dict]: + cur = conn.execute("SELECT id, name FROM bots ORDER BY name") + return [{"id": r[0], "name": r[1]} for r in cur] + + +def get_you(conn: Connection) -> dict | None: + row = conn.execute("SELECT name, pronouns, persona FROM you_entity WHERE id = 1").fetchone() + if not row: + return None + return {"name": row[0], "pronouns": row[1], "persona": row[2]} diff --git a/chat/state/manual_edit.py b/chat/state/manual_edit.py new file mode 100644 index 0000000..e796a7a --- /dev/null +++ b/chat/state/manual_edit.py @@ -0,0 +1,91 @@ +"""Handler for ``manual_edit`` events (T25, §6.4 final paragraph). + +A ``manual_edit`` event captures a user override of a projected field — its +payload snapshots both the prior value and the new value so any edit can +be reversed by emitting an inverse ``manual_edit`` later. This module +applies the new value to the appropriate target table; the snapshot of +``prior_value`` is taken by the route handler before this fires. + +Phase 1 covers four target kinds: +- ``edge_affinity`` and ``edge_trust`` — slider edits on a specific edge, + clamped to 0..100. +- ``memory_significance`` — dropdown edit, clamped to 0..3. +- ``memory_pov_summary`` — textarea edit (string). Also reused by T27's + scene-close pipeline to rewrite per-turn raw narratives into a proper + per-POV scene summary. +- ``edge_summary`` — string overwrite of the directed edge's ``summary`` + field. Driven by T27 from the classifier's ``relationship_summary`` + output combined with the prior summary. + +Other §6.4 editable fields (activity verb / attention / posture, +knowledge_facts list manipulation) are deferred to Phase 1.5. + +Pin toggles intentionally use the existing ``memory_pin_changed`` event +(registered in :mod:`chat.state.memory`) rather than ``manual_edit`` so +the projection writes both ``pinned`` and ``auto_pinned`` atomically. +""" + +from __future__ import annotations + +from sqlite3 import Connection + +from chat.eventlog.log import Event +from chat.eventlog.projector import on + + +def _clamp(value: int, lo: int, hi: int) -> int: + return max(lo, min(hi, value)) + + +@on("manual_edit") +def _apply_manual_edit(conn: Connection, e: Event) -> None: + p = e.payload + kind = p["target_kind"] + target_id = p["target_id"] + new_value = p["new_value"] + + if kind == "edge_affinity": + conn.execute( + "UPDATE edges SET affinity = ? " + "WHERE source_id = ? AND target_id = ?", + ( + _clamp(int(new_value), 0, 100), + target_id["source_id"], + target_id["target_id"], + ), + ) + elif kind == "edge_trust": + conn.execute( + "UPDATE edges SET trust = ? " + "WHERE source_id = ? AND target_id = ?", + ( + _clamp(int(new_value), 0, 100), + target_id["source_id"], + target_id["target_id"], + ), + ) + elif kind == "memory_significance": + conn.execute( + "UPDATE memories SET significance = ? WHERE id = ?", + (_clamp(int(new_value), 0, 3), int(target_id)), + ) + elif kind == "memory_pov_summary": + conn.execute( + "UPDATE memories SET pov_summary = ? WHERE id = ?", + (str(new_value), int(target_id)), + ) + elif kind == "edge_summary": + # ``target_id`` here is a {"source_id", "target_id"} pair like + # the affinity/trust edits, since edges are keyed by the + # directed pair, not a single rowid. + conn.execute( + "UPDATE edges SET summary = ? " + "WHERE source_id = ? AND target_id = ?", + ( + str(new_value), + target_id["source_id"], + target_id["target_id"], + ), + ) + # Unknown target_kind: silently no-op for v1. Future kinds (activity + # fields, knowledge_facts list manipulation) extend the dispatch above. diff --git a/chat/state/memory.py b/chat/state/memory.py new file mode 100644 index 0000000..0426067 --- /dev/null +++ b/chat/state/memory.py @@ -0,0 +1,166 @@ +from __future__ import annotations +from sqlite3 import Connection +from chat.eventlog.projector import on +from chat.eventlog.log import Event + +_VALID_WITNESS_ROLES = {"you", "host", "guest"} + + +def _row_to_dict(conn: Connection, row: tuple) -> dict: + cols = [c[1] for c in conn.execute("PRAGMA table_info(memories)").fetchall()] + return dict(zip(cols, row)) + + +@on("memory_written") +def _apply_memory_written(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "INSERT INTO memories (" + "owner_id, chat_id, scene_id, pov_summary, " + "witness_you, witness_host, witness_guest, " + "chat_clock_at, source, reliability, significance, pinned, auto_pinned" + ") VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", + ( + p["owner_id"], + p["chat_id"], + p.get("scene_id"), + p["pov_summary"], + int(p["witness_you"]), + int(p["witness_host"]), + int(p["witness_guest"]), + p.get("chat_clock_at"), + p.get("source", "direct"), + float(p.get("reliability", 1.0)), + int(p.get("significance", 1)), + int(p.get("pinned", 0)), + int(p.get("auto_pinned", 0)), + ), + ) + + +@on("memory_significance_set") +def _apply_memory_significance_set(conn: Connection, e: Event) -> None: + """Update an existing memory's significance score (T22). + + Emitted by the async significance worker after it scores the turn. + """ + p = e.payload + conn.execute( + "UPDATE memories SET significance = ? WHERE id = ?", + (int(p["significance"]), int(p["memory_id"])), + ) + + +@on("memory_pin_changed") +def _apply_memory_pin_changed(conn: Connection, e: Event) -> None: + """Toggle a memory's pin state (T22, §8.5). + + Used both for auto-pinning a pivotal turn and for evicting the oldest + auto-pin when the per-owner soft cap is exceeded. Manual pins use the + same handler; the ``auto_pinned`` flag distinguishes them so the + eviction query can leave manual pins alone. + """ + p = e.payload + conn.execute( + "UPDATE memories SET pinned = ?, auto_pinned = ? WHERE id = ?", + (int(p["pinned"]), int(p["auto_pinned"]), int(p["memory_id"])), + ) + + +def get_memory(conn: Connection, memory_id: int) -> dict | None: + row = conn.execute( + "SELECT * FROM memories WHERE id = ?", (memory_id,) + ).fetchone() + if not row: + return None + return _row_to_dict(conn, row) + + +def get_pinned(conn: Connection, owner_id: str) -> list[dict]: + cur = conn.execute( + "SELECT * FROM memories WHERE owner_id = ? AND pinned = 1 " + "ORDER BY created_at DESC, id DESC", + (owner_id,), + ) + rows = cur.fetchall() + cols = [c[1] for c in conn.execute("PRAGMA table_info(memories)").fetchall()] + return [dict(zip(cols, row)) for row in rows] + + +# Composite-score weights used by ``search_memories`` (T23, §8 retrieval). +# FTS5 BM25 ``rank`` is *more negative* for better matches, so subtracting a +# positive boost from it drives stronger candidates further down (i.e. earlier +# in an ascending sort). Hardcoded for v1 — tunable in a later pass. +_SIGNIFICANCE_WEIGHT = 0.3 +_RECENCY_WEIGHT = 0.5 + + +def search_memories( + conn: Connection, + owner_id: str, + witness_role: str, + query: str, + k: int = 4, +) -> list[dict]: + """FTS5 search over pov_summary, scoped by owner and witness role. + + witness_role must be one of {"you", "host", "guest"} per the witness flags + on each memory row. Returns up to ``k`` rows ranked by a composite score + that combines the FTS5 BM25 rank with two boosts (§8 retrieval rules): + + * **significance boost** — ``0.3 * significance`` (0..3 per §11.1). + * **recency boost** — ``0.5 * (id / max_id)``, using the row id as a + monotonic recency proxy. Newer memories therefore tilt above older ones + when the BM25 rank and significance are otherwise tied. + + BM25 returns negative scores (lower = better). Both boosts are subtracted + so that stronger candidates yield smaller composite scores; the result is + sorted ascending and truncated to ``k``. The unmodified ``fts_rank`` and a + debug-friendly ``composite_score`` are kept on each returned dict. + """ + if witness_role not in _VALID_WITNESS_ROLES: + raise ValueError( + f"witness_role must be one of {sorted(_VALID_WITNESS_ROLES)}, " + f"got {witness_role!r}" + ) + if not query.strip(): + return [] + witness_col = f"witness_{witness_role}" + cols = [c[1] for c in conn.execute("PRAGMA table_info(memories)").fetchall()] + select_list = ", ".join(f"m.{c}" for c in cols) + # Over-fetch from FTS so the Python-side re-rank has room to reorder + # results that BM25 alone would have demoted past the top-k boundary. + over_fetch = max(k * 4, 20) + sql = ( + f"SELECT {select_list}, memories_fts.rank AS fts_rank " + "FROM memories_fts " + "JOIN memories m ON m.id = memories_fts.rowid " + f"WHERE m.owner_id = ? AND m.{witness_col} = 1 " + "AND memories_fts MATCH ? " + "ORDER BY memories_fts.rank " + "LIMIT ?" + ) + cur = conn.execute(sql, (owner_id, query, over_fetch)) + rows = cur.fetchall() + if not rows: + return [] + + # Recency normalises against the current max id for this owner so the + # boost magnitude is bounded regardless of dataset size. + max_id_row = conn.execute( + "SELECT MAX(id) FROM memories WHERE owner_id = ?", (owner_id,) + ).fetchone() + max_id = max_id_row[0] if max_id_row and max_id_row[0] else 1 + + result_cols = cols + ["fts_rank"] + enriched: list[dict] = [] + for row in rows: + d = dict(zip(result_cols, row)) + fts_rank = d.get("fts_rank") or 0.0 + sig_boost = _SIGNIFICANCE_WEIGHT * (d.get("significance") or 0) + recency_boost = _RECENCY_WEIGHT * ((d.get("id") or 0) / max_id) + d["composite_score"] = fts_rank - sig_boost - recency_boost + enriched.append(d) + + enriched.sort(key=lambda x: x["composite_score"]) + return enriched[:k] diff --git a/chat/state/world.py b/chat/state/world.py new file mode 100644 index 0000000..5966924 --- /dev/null +++ b/chat/state/world.py @@ -0,0 +1,202 @@ +from __future__ import annotations +import json +from sqlite3 import Connection +from chat.eventlog.projector import on +from chat.eventlog.log import Event + + +def _row_to_dict(conn: Connection, table: str, row: tuple) -> dict: + cols = [c[1] for c in conn.execute(f"PRAGMA table_info({table})").fetchall()] + return dict(zip(cols, row)) + + +@on("chat_created") +def _apply_chat_created(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "INSERT INTO chats (id, host_bot_id, guest_bot_id) VALUES (?, ?, ?)", + (p["id"], p["host_bot_id"], p.get("guest_bot_id")), + ) + conn.execute( + "INSERT INTO chat_state (chat_id, time, weather, active_scene_id, narrative_anchor) " + "VALUES (?, ?, ?, NULL, ?)", + ( + p["id"], + p["initial_time"], + p.get("weather", ""), + p.get("narrative_anchor", ""), + ), + ) + + +@on("container_created") +def _apply_container_created(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "INSERT INTO containers (chat_id, name, type, properties_json, parent_id) " + "VALUES (?, ?, ?, ?, ?)", + ( + p["chat_id"], + p["name"], + p["type"], + json.dumps(p.get("properties", {})), + p.get("parent_id"), + ), + ) + + +@on("activity_change") +def _apply_activity_change(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "INSERT OR REPLACE INTO activity (" + "entity_id, container_id, slot, posture, action_json, " + "attention, holding_json, status_json, updated_at" + ") VALUES (?, ?, ?, ?, ?, ?, ?, ?, datetime('now'))", + ( + p["entity_id"], + p.get("container_id"), + p.get("slot"), + p.get("posture", ""), + json.dumps(p.get("action", {})), + p.get("attention", ""), + json.dumps(p.get("holding", [])), + json.dumps(p.get("status", {})), + ), + ) + + +@on("scene_opened") +def _apply_scene_opened(conn: Connection, e: Event) -> None: + p = e.payload + cur = conn.execute( + "INSERT INTO scenes (chat_id, container_id, started_at, ended_at, " + "significance, participants_json) VALUES (?, ?, ?, NULL, 0, ?)", + ( + p["chat_id"], + p.get("container_id"), + p["started_at"], + json.dumps(p.get("participants", [])), + ), + ) + new_id = cur.lastrowid + conn.execute( + "UPDATE chat_state SET active_scene_id = ? WHERE chat_id = ?", + (new_id, p["chat_id"]), + ) + + +@on("scene_closed") +def _apply_scene_closed(conn: Connection, e: Event) -> None: + p = e.payload + scene_id = p["scene_id"] + significance = int(p.get("significance", 0)) + conn.execute( + "UPDATE scenes SET ended_at = ?, significance = ? WHERE id = ?", + (p["ended_at"], significance, scene_id), + ) + row = conn.execute( + "SELECT chat_id FROM scenes WHERE id = ?", (scene_id,) + ).fetchone() + if row is not None: + chat_id = row[0] + conn.execute( + "UPDATE chat_state SET active_scene_id = NULL WHERE chat_id = ?", + (chat_id,), + ) + + +def _chat_select_columns() -> str: + return ( + "c.id, c.host_bot_id, c.guest_bot_id, c.created_at, " + "s.time, s.weather, s.active_scene_id, s.narrative_anchor" + ) + + +def _chat_row_to_dict(row: tuple) -> dict: + return { + "id": row[0], + "host_bot_id": row[1], + "guest_bot_id": row[2], + "created_at": row[3], + "time": row[4], + "weather": row[5], + "active_scene_id": row[6], + "narrative_anchor": row[7], + } + + +def get_chat(conn: Connection, chat_id: str) -> dict | None: + row = conn.execute( + f"SELECT {_chat_select_columns()} FROM chats c " + "JOIN chat_state s ON s.chat_id = c.id WHERE c.id = ?", + (chat_id,), + ).fetchone() + if not row: + return None + return _chat_row_to_dict(row) + + +def list_chats(conn: Connection) -> list[dict]: + cur = conn.execute( + f"SELECT {_chat_select_columns()} FROM chats c " + "JOIN chat_state s ON s.chat_id = c.id ORDER BY c.id" + ) + return [_chat_row_to_dict(row) for row in cur.fetchall()] + + +def get_container(conn: Connection, container_id: int) -> dict | None: + row = conn.execute( + "SELECT * FROM containers WHERE id = ?", (container_id,) + ).fetchone() + if not row: + return None + d = _row_to_dict(conn, "containers", row) + d["properties"] = json.loads(d.pop("properties_json")) + return d + + +def find_container(conn: Connection, chat_id: str, name: str) -> dict | None: + row = conn.execute( + "SELECT * FROM containers WHERE chat_id = ? AND name = ?", + (chat_id, name), + ).fetchone() + if not row: + return None + d = _row_to_dict(conn, "containers", row) + d["properties"] = json.loads(d.pop("properties_json")) + return d + + +def get_activity(conn: Connection, entity_id: str) -> dict | None: + row = conn.execute( + "SELECT * FROM activity WHERE entity_id = ?", (entity_id,) + ).fetchone() + if not row: + return None + d = _row_to_dict(conn, "activity", row) + d["action"] = json.loads(d.pop("action_json")) + d["holding"] = json.loads(d.pop("holding_json")) + d["status"] = json.loads(d.pop("status_json")) + return d + + +def get_scene(conn: Connection, scene_id: int) -> dict | None: + row = conn.execute( + "SELECT * FROM scenes WHERE id = ?", (scene_id,) + ).fetchone() + if not row: + return None + d = _row_to_dict(conn, "scenes", row) + d["participants"] = json.loads(d.pop("participants_json")) + return d + + +def active_scene(conn: Connection, chat_id: str) -> dict | None: + row = conn.execute( + "SELECT active_scene_id FROM chat_state WHERE chat_id = ?", + (chat_id,), + ).fetchone() + if not row or row[0] is None: + return None + return get_scene(conn, row[0]) diff --git a/chat/static/app.css b/chat/static/app.css new file mode 100644 index 0000000..66e76ef --- /dev/null +++ b/chat/static/app.css @@ -0,0 +1,125 @@ +* { box-sizing: border-box; } +body { + font: 15px/1.5 system-ui, -apple-system, "Segoe UI", sans-serif; + margin: 0; + color: #1c1c1c; + background: #fafafa; + display: flex; + min-height: 100vh; +} +.rail { + width: 200px; + background: #1c1c1c; + color: #fff; + padding: 16px; + flex-shrink: 0; +} +.rail a { color: #fff; text-decoration: none; } +.rail-brand { + font-weight: 600; + display: block; + padding-bottom: 16px; + border-bottom: 1px solid #333; + margin-bottom: 16px; +} +.rail ul { list-style: none; padding: 0; margin: 0; } +.rail li { margin: 4px 0; } +.rail li a { display: block; padding: 6px 8px; border-radius: 3px; } +.rail li a.active { background: #333; } +.content { + flex: 1; + padding: 24px; + background: #fafafa; + overflow: auto; +} +.brand { font-weight: 600; text-decoration: none; color: inherit; } +.container { max-width: 720px; margin: 24px auto; padding: 0 16px; } +h1 { margin-top: 0; } +.page-header { display: flex; align-items: center; justify-content: space-between; } +.btn, button { + display: inline-block; padding: 8px 14px; + border: 1px solid #444; background: #1c1c1c; color: #fff; + border-radius: 4px; text-decoration: none; cursor: pointer; + font: inherit; +} +.bot-form label { display: block; margin-bottom: 14px; } +.bot-form label span { display: block; font-weight: 600; margin-bottom: 4px; } +.bot-form input[type=text], .bot-form textarea { + width: 100%; padding: 6px 8px; font: inherit; + border: 1px solid #ccc; border-radius: 3px; background: #fff; +} +.bot-form small { display: block; color: #666; margin-top: 2px; } +.bot-list { list-style: none; padding: 0; } +.bot-list li { padding: 8px 0; border-bottom: 1px solid #eee; } +.chat-list { list-style: none; padding: 0; margin: 0; } +.chat-row { border-bottom: 1px solid #eee; } +.chat-row a { display: block; padding: 12px 0; text-decoration: none; color: inherit; } +.chat-row a:hover { background: #f0f0f0; } +.chat-row-name { font-weight: 600; } +.chat-row-snippet { font-size: 14px; } +.chat-row-meta { font-size: 12px; } +.muted { color: #666; } +.error { + padding: 8px 12px; border: 1px solid #c33; background: #fdecea; + color: #a00; border-radius: 3px; +} +.success { + padding: 8px 12px; border: 1px solid #2d7a3a; background: #eafaf0; + color: #1f5c2a; border-radius: 3px; +} +code { font-family: ui-monospace, "SF Mono", Menlo, monospace; } +.chat-shell { display: flex; flex-direction: column; height: 100%; max-width: 760px; margin: 0 auto; } +.chat-header { display: flex; align-items: center; gap: 16px; border-bottom: 1px solid #e5e5e5; padding-bottom: 8px; margin-bottom: 16px; } +.chat-header h1 { margin: 0; flex: 1; } +.chat-meta { font-size: 13px; } +.drawer-toggle { padding: 4px 10px; border: 1px solid #ccc; background: #fff; color: #1c1c1c; border-radius: 3px; cursor: pointer; } +.timeline { flex: 1; overflow-y: auto; min-height: 200px; padding: 8px 0; } +.turn { margin: 12px 0; } +.turn strong { display: block; margin-bottom: 4px; } +.turn p { margin: 0 0 8px; } +.turn p:last-child { margin-bottom: 0; } +.turn-you strong { color: #1a73e8; } +.turn-bot strong { color: #1c1c1c; } +/* ``*action*`` — italic narration. */ +.action { font-style: italic; color: #555; } +/* ``((ooc))`` — author-to-system aside. Dim, italic, smaller, set off + from surrounding prose so it doesn't read as in-fiction speech. */ +.ooc { + font-style: italic; + font-size: 12px; + color: #999; + display: inline-block; + background: rgba(0, 0, 0, 0.04); + padding: 1px 4px; + border-radius: 3px; +} +.turn blockquote { + border-left: 3px solid #ccc; + padding-left: 12px; + margin: 8px 0; + color: #555; +} +.turn-input { display: flex; flex-direction: column; gap: 8px; padding-top: 12px; border-top: 1px solid #e5e5e5; } +.turn-input textarea { padding: 8px; font: inherit; border: 1px solid #ccc; border-radius: 3px; resize: vertical; } +.drawer { position: fixed; top: 0; right: 0; width: 360px; height: 100vh; background: #fff; border-left: 1px solid #e5e5e5; padding: 16px; overflow-y: auto; z-index: 10; } +.drawer[hidden] { display: none; } +.drawer-content { display: flex; flex-direction: column; gap: 16px; } +.drawer-header { display: flex; align-items: center; justify-content: space-between; padding-bottom: 8px; border-bottom: 1px solid #e5e5e5; } +.drawer-close { border: none; background: transparent; color: #1c1c1c; font-size: 24px; padding: 0 4px; cursor: pointer; } +.drawer-section h3 { margin: 0 0 8px; font-size: 14px; text-transform: uppercase; letter-spacing: 0.5px; color: #666; } +.activity-row, .edge-row { margin-bottom: 12px; } +.activity-row strong, .edge-row strong { display: block; } +.memory-list { list-style: none; padding: 0; margin: 0; } +.memory-list li { padding: 4px 0; font-size: 13px; } +.sig { display: inline-block; min-width: 16px; } +.sig-3 { color: #d4af37; } +/* Streaming UX (T34): typing indicator, Stop button, disconnect banner. */ +.streaming { opacity: 0.85; } +.streaming-text:after { + content: "\025AE"; + margin-left: 2px; + animation: blink 1s steps(2, start) infinite; +} +@keyframes blink { to { visibility: hidden; } } +.stop-streaming { background: #c33; border-color: #a00; margin-bottom: 8px; align-self: flex-start; } +.connection-lost { margin-bottom: 8px; } diff --git a/chat/templates/_drawer.html b/chat/templates/_drawer.html new file mode 100644 index 0000000..4ebfc22 --- /dev/null +++ b/chat/templates/_drawer.html @@ -0,0 +1,139 @@ +
+
+

{{ host_bot.name }}

+ +
+ +
+

Scene

+ {% if scene %} +

Started: {{ scene.started_at }}

+ {% endif %} + {% if container %} +

Container: {{ container.name }} ({{ container.type }})

+ {% else %} +

No active container.

+ {% endif %} +

Time: {{ chat.time }}

+ {% if scene %} +
+ +
+ {% else %} +

No active scene.

+ {% endif %} +
+ +
+

Activity

+ {% for label, act in [("you", you_activity), (host_bot.name, bot_activity)] %} +
+ {{ label }} + {% if act %} +

{{ act.posture or "—" }} / {{ (act.action or {}).verb or "—" }}

+ {% if act.attention %}

attention: {{ act.attention }}

{% endif %} + {% if act.holding %}

holding: {{ act.holding|join(", ") }}

{% endif %} + {% else %} +

No activity recorded.

+ {% endif %} +
+ {% endfor %} +
+ +
+

Edges

+ {% if edge_b2y %} +
+ {{ host_bot.name }} → you +

Affinity: {{ edge_b2y.affinity }}/100 · Trust: {{ edge_b2y.trust }}/100

+
+ + +
+ {% if edge_b2y.summary %}

{{ edge_b2y.summary }}

{% endif %} + {% if edge_b2y.knowledge %} +
Knowledge ({{ edge_b2y.knowledge|length }}) +
    {% for fact in edge_b2y.knowledge %}
  • {{ fact }}
    • {% endfor %}
+
+ {% endif %} +
+ {% endif %} + {% if edge_y2b %} +
+ you → {{ host_bot.name }} +

Affinity: {{ edge_y2b.affinity }}/100 · Trust: {{ edge_y2b.trust }}/100

+ {% if edge_y2b.summary %}

{{ edge_y2b.summary }}

{% endif %} +
+ {% endif %} + {% if not edge_b2y and not edge_y2b %} +

No edges yet.

+ {% endif %} +
+ +
+

Pinned memories ({{ pinned|length }} / {{ pin_cap }})

+ {% if pinned %} +
    + {% for m in pinned %} +
  • + {{ ['·','•','★','★★'][m.significance|default(0)] }} + {{ m.pov_summary }} +
    + + +
    +
    • + {% endfor %} +
+ {% else %} +

No pinned memories.

+ {% endif %} +
+ +
+

Recent memories

+ {% if recent_memories %} +
    + {% for m in recent_memories %} +
  • + {{ ['·','•','★','★★'][m.significance|default(0)] }} + {{ m.pov_summary[:200] }}{% if m.pov_summary|length > 200 %}…{% endif %} +
    + + +
    +
    + + +
    +
    • + {% endfor %} +
+ {% else %} +

No memories yet.

+ {% endif %} +
+
diff --git a/chat/templates/base.html b/chat/templates/base.html new file mode 100644 index 0000000..01d0abd --- /dev/null +++ b/chat/templates/base.html @@ -0,0 +1,13 @@ + + + + + + {% block title %}chat{% endblock %} + + + + + {% block body %}{% endblock %} + + diff --git a/chat/templates/bot_form.html b/chat/templates/bot_form.html new file mode 100644 index 0000000..6d44080 --- /dev/null +++ b/chat/templates/bot_form.html @@ -0,0 +1,57 @@ +{% extends "layout.html" %} +{% block title %}New bot - chat{% endblock %} +{% block content %} +

New bot

+{% if error %} +

{{ error }}

+{% endif %} +
+ + + + + + + + + + + + + + + + + +
+{% endblock %} diff --git a/chat/templates/bot_list.html b/chat/templates/bot_list.html new file mode 100644 index 0000000..247d886 --- /dev/null +++ b/chat/templates/bot_list.html @@ -0,0 +1,28 @@ +{% extends "layout.html" %} +{% block title %}Bots - chat{% endblock %} +{% block content %} +
+

Bots

+ + New bot +
+{% if bots %} +
    + {% for bot in bots %} +
  • + {{ bot.name }} +
    + Reset +
    + + +
    +
    +
    • + {% endfor %} +
+{% else %} +

No bots yet. Create your first bot.

+{% endif %} +{% endblock %} diff --git a/chat/templates/chat.html b/chat/templates/chat.html new file mode 100644 index 0000000..c2f622c --- /dev/null +++ b/chat/templates/chat.html @@ -0,0 +1,159 @@ +{% extends "layout.html" %} +{% block title %}{{ host_bot.name }} - chat{% endblock %} +{% block content %} +
+
+

{{ host_bot.name }}

+
{{ chat.time }}
+ +
+ +
+ {% if not turns %} +

No turns yet. Start typing below.

+ {% else %} + {% for turn in turns %} +
+ {{ turn.speaker }} + {{ turn.text|render_prose|safe }} +
+ {% endfor %} + {% endif %} +
+ +
+ + +
+ + +
+ + +{% endblock %} diff --git a/chat/templates/chat_list.html b/chat/templates/chat_list.html new file mode 100644 index 0000000..a16a1ed --- /dev/null +++ b/chat/templates/chat_list.html @@ -0,0 +1,26 @@ +{% extends "layout.html" %} +{% block title %}Chats - chat{% endblock %} +{% block content %} +
+

Chats

+ + New bot +
+{% if chats %} + +{% else %} +

No chats yet. Create a bot to start.

+{% endif %} +{% endblock %} diff --git a/chat/templates/errors.html b/chat/templates/errors.html new file mode 100644 index 0000000..85f44e0 --- /dev/null +++ b/chat/templates/errors.html @@ -0,0 +1,9 @@ +{% extends "layout.html" %} +{% block title %}Error - chat{% endblock %} +{% block content %} +
+

{{ status_code }}

+

{{ detail }}

+

Back to chats

+
+{% endblock %} diff --git a/chat/templates/kickoff_confirm.html b/chat/templates/kickoff_confirm.html new file mode 100644 index 0000000..56f6753 --- /dev/null +++ b/chat/templates/kickoff_confirm.html @@ -0,0 +1,118 @@ +{% extends "layout.html" %} +{% block title %}Confirm kickoff - chat{% endblock %} +{% block content %} +

Confirm kickoff

+

Review and edit the parsed opening scene for {{ values.bot_name }}, then confirm to start the chat.

+ +
+ +
+ Container + + + +
+ +
+ Initial in-fiction time + +
+ +
+ Your activity + + + + + + + +
+ +
+ {{ values.bot_name }}'s activity + + + + + + + +
+ +
+ Edge seed + + +
+ +
+ + Cancel +
+
+{% endblock %} diff --git a/chat/templates/layout.html b/chat/templates/layout.html new file mode 100644 index 0000000..7b1954b --- /dev/null +++ b/chat/templates/layout.html @@ -0,0 +1,14 @@ +{% extends "base.html" %} +{% block body %} + +
+ {% block content %}{% endblock %} +
+{% endblock %} diff --git a/chat/templates/settings.html b/chat/templates/settings.html new file mode 100644 index 0000000..26671f8 --- /dev/null +++ b/chat/templates/settings.html @@ -0,0 +1,29 @@ +{% extends "layout.html" %} +{% block title %}Settings - chat{% endblock %} +{% block content %} +

Settings

+{% if saved %} +

Settings saved.

+{% endif %} +
+ + + + + + + +
+{% endblock %} diff --git a/chat/web/__init__.py b/chat/web/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/chat/web/bots.py b/chat/web/bots.py new file mode 100644 index 0000000..d9666f3 --- /dev/null +++ b/chat/web/bots.py @@ -0,0 +1,139 @@ +from __future__ import annotations +import sqlite3 +from pathlib import Path +from fastapi import APIRouter, Depends, Form, HTTPException, Request +from fastapi.responses import RedirectResponse, HTMLResponse +from fastapi.templating import Jinja2Templates + +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.state.entities import list_bots + +TEMPLATES = Jinja2Templates(directory=str(Path(__file__).resolve().parent.parent / "templates")) + +router = APIRouter() + +REQUIRED_FIELDS = ("id", "name", "persona", "initial_relationship_to_you", "kickoff_prose") + + +def get_conn(request: Request): + settings = request.app.state.settings + db_path: Path = settings.db_path + db_path.parent.mkdir(parents=True, exist_ok=True) + conn = sqlite3.connect(db_path, check_same_thread=False) + conn.execute("PRAGMA journal_mode=WAL") + conn.execute("PRAGMA foreign_keys=ON") + try: + yield conn + conn.commit() + finally: + conn.close() + + +def _split_voice_samples(text: str) -> list[str]: + if not text or not text.strip(): + return [] + # Split on a line containing only "---" (with optional surrounding whitespace). + parts: list[str] = [] + buf: list[str] = [] + for line in text.splitlines(): + if line.strip() == "---": + if buf: + parts.append("\n".join(buf).strip()) + buf = [] + continue + buf.append(line) + if buf: + parts.append("\n".join(buf).strip()) + return [p for p in parts if p] + + +def _split_traits(text: str) -> list[str]: + if not text or not text.strip(): + return [] + items: list[str] = [] + for line in text.splitlines(): + line = line.strip() + if not line: + continue + if "," in line: + items.extend(p.strip() for p in line.split(",")) + else: + items.append(line) + return [t for t in items if t] + + +@router.get("/bots", response_class=HTMLResponse) +async def bots_list(request: Request, conn=Depends(get_conn)): + bots = list_bots(conn) + return TEMPLATES.TemplateResponse( + request, "bot_list.html", {"bots": bots, "active_nav": "bots"} + ) + + +@router.get("/bots/new", response_class=HTMLResponse) +async def bot_form(request: Request): + return TEMPLATES.TemplateResponse( + request, "bot_form.html", {"values": {}, "error": None, "active_nav": "bots"} + ) + + +@router.post("/bots/new") +async def bot_create( + request: Request, + id: str = Form(""), + name: str = Form(""), + persona: str = Form(""), + voice_samples: str = Form(""), + traits: str = Form(""), + backstory: str = Form(""), + initial_relationship_to_you: str = Form(""), + kickoff_prose: str = Form(""), + conn=Depends(get_conn), +): + values = { + "id": id, + "name": name, + "persona": persona, + "voice_samples": voice_samples, + "traits": traits, + "backstory": backstory, + "initial_relationship_to_you": initial_relationship_to_you, + "kickoff_prose": kickoff_prose, + } + missing = [f for f in REQUIRED_FIELDS if not values[f].strip()] + if missing: + raise HTTPException(status_code=400, detail=f"missing required: {', '.join(missing)}") + + payload = { + "id": id.strip(), + "name": name.strip(), + "persona": persona.strip(), + "voice_samples": _split_voice_samples(voice_samples), + "traits": _split_traits(traits), + "backstory": backstory.strip(), + "initial_relationship_to_you": initial_relationship_to_you.strip(), + "kickoff_prose": kickoff_prose.strip(), + } + append_event(conn, kind="bot_authored", payload=payload) + project(conn) + return RedirectResponse(url=f"/bots/{payload['id']}/kickoff", status_code=303) + + +@router.post("/bots/{bot_id}/reset") +async def reset_bot_route( + bot_id: str, + request: Request, + confirm_name: str = Form(""), + conn=Depends(get_conn), +): + from chat.services.reset import reset_bot + + try: + reset_bot(conn, bot_id, confirm_name=confirm_name) + except ValueError as e: + msg = str(e).lower() + if "not found" in msg: + raise HTTPException(status_code=404, detail=str(e)) + raise HTTPException(status_code=400, detail=str(e)) + return RedirectResponse(url="/bots", status_code=303) diff --git a/chat/web/chat.py b/chat/web/chat.py new file mode 100644 index 0000000..0486d8e --- /dev/null +++ b/chat/web/chat.py @@ -0,0 +1,71 @@ +"""Chat detail (shell) page. + +Renders ``/chats/``: the title (host bot's name), a timeline placeholder, +the user-input form, and the drawer toggle. Turn handling lives in T19; this +module only sets up the structural shell. +""" + +from __future__ import annotations + +from pathlib import Path + +from fastapi import APIRouter, Depends, HTTPException, Request +from fastapi.responses import HTMLResponse +from fastapi.templating import Jinja2Templates + +from chat.state.entities import get_bot +from chat.state.world import get_chat +from chat.web.bots import get_conn +from chat.web.render import render_prose +from chat.web.turns import _read_recent_dialogue + +TEMPLATES = Jinja2Templates( + directory=str(Path(__file__).resolve().parent.parent / "templates") +) +# Register the prose renderer as a Jinja filter so the chat-detail +# template can use ``{{ turn.text|render_prose|safe }}`` (Task 33). +# The renderer escapes user content internally; ``|safe`` is required +# because the output contains intentional ``

``/````/etc. tags. +TEMPLATES.env.filters["render_prose"] = render_prose + +router = APIRouter() + + +@router.get("/chats/{chat_id}", response_class=HTMLResponse) +async def chat_detail(chat_id: str, request: Request, conn=Depends(get_conn)): + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + + host_bot = get_bot(conn, chat["host_bot_id"]) + if host_bot is None: + # Defensive: chat row references a bot that doesn't exist. Treat as 404 + # rather than crashing the template render. + raise HTTPException( + status_code=404, detail=f"host bot not found: {chat['host_bot_id']}" + ) + + # T19: render the timeline from event_log. We pull both user_turn and + # assistant_turn events for this chat, in chronological order. Each row + # is shaped ``{"speaker": ..., "text": ...}`` and the template + # discriminates roles via the speaker id (the literal "you" vs. a bot id). + raw_turns = _read_recent_dialogue(conn, chat_id, limit=200) + turns: list[dict] = [] + for t in raw_turns: + if t["speaker"] == "you": + turns.append({"role": "you", "speaker": "you", "text": t["text"]}) + else: + bot = get_bot(conn, t["speaker"]) + label = bot["name"] if bot else t["speaker"] + turns.append({"role": "bot", "speaker": label, "text": t["text"]}) + + return TEMPLATES.TemplateResponse( + request, + "chat.html", + { + "chat": chat, + "host_bot": host_bot, + "turns": turns, + "active_nav": "chats", + }, + ) diff --git a/chat/web/drawer.py b/chat/web/drawer.py new file mode 100644 index 0000000..3b61e50 --- /dev/null +++ b/chat/web/drawer.py @@ -0,0 +1,306 @@ +"""Chat drawer — read view (T24) and inline edits (T25). + +The GET endpoint renders an HTML partial showing the current scene + +container, per-entity activity, host <-> you edges, pinned memories with +an ``n / cap`` counter, and recent witnessed memories from the host's +POV with significance markers. + +T25 adds three POST endpoints for the most useful inline edits, each +returning the refreshed drawer partial so HTMX can swap it in: + +* affinity slider on an edge (emits ``manual_edit``); +* significance dropdown on a memory (emits ``manual_edit``); +* pin toggle on a memory (emits ``memory_pin_changed`` with + ``auto_pinned=0`` so a manual pin is not subject to auto-eviction). + +Each ``manual_edit`` payload snapshots the prior value alongside the new +one so a later inverse edit can restore state (§6.4 final paragraph). + +Other §6.4 editable fields (activity verb/attention/posture, edge_trust, +edge summary, knowledge_facts list, memory pov_summary) are deferred to +a Phase 1.5 follow-up — the dispatch in :mod:`chat.state.manual_edit` +already accepts more ``target_kind`` values, so adding their routes is a +mechanical extension. +""" + +from __future__ import annotations + +from pathlib import Path + +from fastapi import APIRouter, Depends, Form, HTTPException, Request +from fastapi.responses import HTMLResponse +from fastapi.templating import Jinja2Templates + +from chat.eventlog.log import append_and_apply +from chat.services.scene_summarize import apply_scene_close_summary +from chat.state.edges import get_edge +from chat.state.entities import get_bot, get_you +from chat.state.memory import get_pinned +from chat.state.world import active_scene, get_activity, get_chat, get_container +from chat.web.bots import get_conn +from chat.web.kickoff import get_llm_client + +TEMPLATES = Jinja2Templates( + directory=str(Path(__file__).resolve().parent.parent / "templates") +) + +router = APIRouter() + +# Soft cap on pinned memories per owner (§8.5). Surfaced in the drawer header +# as `pinned|length / pin_cap`; eviction logic itself lives in T22. +PIN_CAP = 8 + +# Recent-memories list is bounded to keep the drawer cheap to render. +RECENT_LIMIT = 10 + + +@router.get("/chats/{chat_id}/drawer", response_class=HTMLResponse) +async def drawer(chat_id: str, request: Request, conn=Depends(get_conn)): + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + + host_bot = get_bot(conn, chat["host_bot_id"]) + if host_bot is None: + raise HTTPException( + status_code=404, detail=f"host bot not found: {chat['host_bot_id']}" + ) + you_entity = get_you(conn) or {"name": "you", "pronouns": "", "persona": ""} + + scene = active_scene(conn, chat_id) + container = None + if scene and scene.get("container_id") is not None: + container = get_container(conn, scene["container_id"]) + + you_activity = get_activity(conn, "you") + bot_activity = get_activity(conn, chat["host_bot_id"]) + + edge_b2y = get_edge(conn, chat["host_bot_id"], "you") + edge_y2b = get_edge(conn, "you", chat["host_bot_id"]) + + # Recent memories from host's POV (witness_host = 1), most recent first. + # Raw query keeps this read self-contained — no projector helper exposes + # "latest N for an owner" yet and the drawer is the only consumer. + recent_rows = conn.execute( + """ + SELECT id, pov_summary, significance, pinned, created_at + FROM memories + WHERE owner_id = ? AND witness_host = 1 + ORDER BY id DESC + LIMIT ? + """, + (chat["host_bot_id"], RECENT_LIMIT), + ).fetchall() + recent_memories = [ + { + "id": r[0], + "pov_summary": r[1], + "significance": r[2], + "pinned": r[3], + "created_at": r[4], + } + for r in recent_rows + ] + + pinned = get_pinned(conn, chat["host_bot_id"]) + + return TEMPLATES.TemplateResponse( + request, + "_drawer.html", + { + "chat": chat, + "host_bot": host_bot, + "you_entity": you_entity, + "scene": scene, + "container": container, + "you_activity": you_activity, + "bot_activity": bot_activity, + "edge_b2y": edge_b2y, + "edge_y2b": edge_y2b, + "recent_memories": recent_memories, + "pinned": pinned, + "pin_cap": PIN_CAP, + }, + ) + + +# --- T25 edit endpoints --------------------------------------------------- +# +# Each endpoint: +# 1. Loads the chat (404 if missing) and the target row (404 if missing). +# 2. Reads the prior value before mutating, so the event payload carries +# it for §6.4 reversibility. +# 3. Calls ``append_and_apply`` so the projected table updates atomically +# with the event log append; full reprojection would re-add deltas +# from earlier ``edge_update`` events. +# 4. Returns the refreshed drawer partial via ``await drawer(...)``, which +# HTMX swaps into ``#drawer``. + + +@router.post( + "/chats/{chat_id}/drawer/scene/close", + response_class=HTMLResponse, +) +async def close_scene_manual( + chat_id: str, + request: Request, + conn=Depends(get_conn), + client=Depends(get_llm_client), +): + """Manual scene close from the drawer button. + + Always available when there's an active scene; mirrors the auto-close + path in the turn flow but bypasses the hard-signal classifier. After + emitting ``scene_closed`` we run the T27 per-POV summary pipeline + (one classifier call) so the manual path produces the same memory / + edge updates as the auto path. Returns the refreshed drawer partial + so HTMX swaps it in. ``400`` when no scene is active — the button is + hidden in that state but a stale tab might still POST. + """ + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + + scene = active_scene(conn, chat_id) + if scene is None: + raise HTTPException( + status_code=400, detail="no active scene to close" + ) + + append_and_apply( + conn, + kind="scene_closed", + payload={ + "scene_id": scene["id"], + "ended_at": chat.get("time"), + # Significance defaults to 0; T22's significance worker + # operates on memories, not scenes. + "significance": 0, + }, + ) + + settings = request.app.state.settings + await apply_scene_close_summary( + conn, + client, + classifier_model=settings.classifier_model, + chat_id=chat_id, + scene_id=scene["id"], + host_bot_id=chat["host_bot_id"], + timeout_s=settings.classifier_timeout_s, + ) + return await drawer(chat_id, request, conn) + + +@router.post( + "/chats/{chat_id}/drawer/edge/{source_id}/{target_id}/affinity", + response_class=HTMLResponse, +) +async def edit_edge_affinity( + chat_id: str, + source_id: str, + target_id: str, + request: Request, + affinity: int = Form(...), + conn=Depends(get_conn), +): + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + + edge = get_edge(conn, source_id, target_id) + if edge is None: + raise HTTPException( + status_code=404, + detail=f"edge not found: {source_id}->{target_id}", + ) + + prior = int(edge["affinity"]) + new_value = max(0, min(100, int(affinity))) + append_and_apply( + conn, + kind="manual_edit", + payload={ + "target_kind": "edge_affinity", + "target_id": {"source_id": source_id, "target_id": target_id}, + "prior_value": prior, + "new_value": new_value, + }, + ) + return await drawer(chat_id, request, conn) + + +@router.post( + "/chats/{chat_id}/drawer/memory/{memory_id}/significance", + response_class=HTMLResponse, +) +async def edit_memory_significance( + chat_id: str, + memory_id: int, + request: Request, + significance: int = Form(...), + conn=Depends(get_conn), +): + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + + row = conn.execute( + "SELECT significance FROM memories WHERE id = ?", (memory_id,) + ).fetchone() + if row is None: + raise HTTPException( + status_code=404, detail=f"memory not found: {memory_id}" + ) + + prior = int(row[0]) + new_value = max(0, min(3, int(significance))) + append_and_apply( + conn, + kind="manual_edit", + payload={ + "target_kind": "memory_significance", + "target_id": int(memory_id), + "prior_value": prior, + "new_value": new_value, + }, + ) + return await drawer(chat_id, request, conn) + + +@router.post( + "/chats/{chat_id}/drawer/memory/{memory_id}/pin", + response_class=HTMLResponse, +) +async def toggle_memory_pin( + chat_id: str, + memory_id: int, + request: Request, + pinned: int = Form(...), + conn=Depends(get_conn), +): + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + + row = conn.execute( + "SELECT pinned FROM memories WHERE id = ?", (memory_id,) + ).fetchone() + if row is None: + raise HTTPException( + status_code=404, detail=f"memory not found: {memory_id}" + ) + + new_pinned = 1 if int(pinned) else 0 + # Manual pin: ``auto_pinned=0`` so the §8.5 eviction query (which only + # touches auto-pinned rows) leaves this alone. + append_and_apply( + conn, + kind="memory_pin_changed", + payload={ + "memory_id": int(memory_id), + "pinned": new_pinned, + "auto_pinned": 0, + }, + ) + return await drawer(chat_id, request, conn) diff --git a/chat/web/kickoff.py b/chat/web/kickoff.py new file mode 100644 index 0000000..320b771 --- /dev/null +++ b/chat/web/kickoff.py @@ -0,0 +1,286 @@ +"""Kickoff parse-and-confirm flow. + +After a bot is authored, the user lands on ``/bots//kickoff``. We call the +LLM-backed ``parse_kickoff`` to extract a structured opening scene from the +authored prose and render it as an editable form. On submit, the (possibly +edited) values are turned into a sequence of events that initialize the chat, +its container, the participants' activities, an open scene, and a seed edge. +""" + +from __future__ import annotations + +import json +from datetime import datetime +from pathlib import Path + +from fastapi import APIRouter, Depends, Form, HTTPException, Request +from fastapi.responses import HTMLResponse, RedirectResponse +from fastapi.templating import Jinja2Templates + +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.llm.client import LLMClient +from chat.services.kickoff import parse_kickoff +from chat.state.entities import get_bot, get_you +from chat.web.bots import get_conn + +TEMPLATES = Jinja2Templates( + directory=str(Path(__file__).resolve().parent.parent / "templates") +) + +router = APIRouter() + + +def get_llm_client(request: Request) -> LLMClient: + """Production LLM client. Tests override this via ``app.dependency_overrides``.""" + settings = request.app.state.settings + from chat.llm.featherless import FeatherlessClient + + return FeatherlessClient( + api_key=settings.featherless_api_key, + base_url=settings.featherless_base_url, + ) + + +def _parse_holding(text: str) -> list[str]: + if not text or not text.strip(): + return [] + return [p.strip() for p in text.split(",") if p.strip()] + + +def _parse_facts(text: str) -> list[str]: + if not text or not text.strip(): + return [] + return [line.strip() for line in text.splitlines() if line.strip()] + + +def _parse_properties(text: str) -> dict: + """Parse the container_properties textarea as JSON. + + Returns ``{}`` on invalid JSON rather than raising — the form is editable + and a bad value should not block the user from confirming the rest. + """ + if not text or not text.strip(): + return {} + try: + loaded = json.loads(text) + return loaded if isinstance(loaded, dict) else {} + except (json.JSONDecodeError, ValueError): + return {} + + +@router.get("/bots/{bot_id}/kickoff", response_class=HTMLResponse) +async def kickoff_get( + bot_id: str, + request: Request, + conn=Depends(get_conn), + llm=Depends(get_llm_client), +): + bot = get_bot(conn, bot_id) + if bot is None: + raise HTTPException(status_code=404, detail=f"bot not found: {bot_id}") + + you = get_you(conn) + you_name = you["name"] if you else "You" + + settings = request.app.state.settings + parsed = await parse_kickoff( + llm, + model=settings.classifier_model, + bot_name=bot["name"], + bot_persona=bot["persona"], + initial_relationship_to_you=bot.get("initial_relationship_to_you", ""), + kickoff_prose=bot.get("kickoff_prose", ""), + you_name=you_name, + timeout_s=settings.classifier_timeout_s, + ) + + # Render values onto the form. ``container_properties`` is shown as JSON; + # ``holding`` lists are rendered as comma-separated text; the seed + # knowledge facts are rendered one-per-line. + values = { + "bot_id": bot_id, + "bot_name": bot["name"], + "container_name": parsed.container_name, + "container_type": parsed.container_type, + "container_properties": json.dumps(parsed.container_properties, indent=2), + "initial_time_iso": parsed.initial_time_iso, + "you_activity_posture": parsed.you_activity.posture, + "you_activity_action_verb": parsed.you_activity.action_verb, + "you_activity_action_interruptible": parsed.you_activity.action_interruptible, + "you_activity_action_required_attention": parsed.you_activity.action_required_attention, + "you_activity_action_expected_duration": parsed.you_activity.action_expected_duration, + "you_activity_attention": parsed.you_activity.attention, + "you_activity_holding": ", ".join(parsed.you_activity.holding), + "bot_activity_posture": parsed.bot_activity.posture, + "bot_activity_action_verb": parsed.bot_activity.action_verb, + "bot_activity_action_interruptible": parsed.bot_activity.action_interruptible, + "bot_activity_action_required_attention": parsed.bot_activity.action_required_attention, + "bot_activity_action_expected_duration": parsed.bot_activity.action_expected_duration, + "bot_activity_attention": parsed.bot_activity.attention, + "bot_activity_holding": ", ".join(parsed.bot_activity.holding), + "edge_seed_summary": parsed.edge_seed_summary, + "edge_seed_knowledge_facts": "\n".join(parsed.edge_seed_knowledge_facts), + } + return TEMPLATES.TemplateResponse( + request, "kickoff_confirm.html", {"values": values, "active_nav": "bots"} + ) + + +@router.post("/bots/{bot_id}/kickoff") +async def kickoff_post( + bot_id: str, + request: Request, + container_name: str = Form(""), + container_type: str = Form(""), + container_properties: str = Form(""), + initial_time_iso: str = Form(""), + you_activity_posture: str = Form(""), + you_activity_action_verb: str = Form(""), + you_activity_action_interruptible: str = Form(""), + you_activity_action_required_attention: str = Form("low"), + you_activity_action_expected_duration: str = Form(""), + you_activity_attention: str = Form(""), + you_activity_holding: str = Form(""), + bot_activity_posture: str = Form(""), + bot_activity_action_verb: str = Form(""), + bot_activity_action_interruptible: str = Form(""), + bot_activity_action_required_attention: str = Form("low"), + bot_activity_action_expected_duration: str = Form(""), + bot_activity_attention: str = Form(""), + bot_activity_holding: str = Form(""), + edge_seed_summary: str = Form(""), + edge_seed_knowledge_facts: str = Form(""), + conn=Depends(get_conn), +): + bot = get_bot(conn, bot_id) + if bot is None: + raise HTTPException(status_code=404, detail=f"bot not found: {bot_id}") + + # Loose ISO 8601 validation. ``datetime.fromisoformat`` accepts the offset + # form ``2026-04-26T20:00:00+00:00`` we use; reject anything it can't parse. + if initial_time_iso.strip(): + try: + datetime.fromisoformat(initial_time_iso.strip()) + except ValueError: + raise HTTPException( + status_code=400, + detail=f"invalid initial_time_iso: {initial_time_iso!r}", + ) + + chat_id = f"chat_{bot_id}" + + # Predict the next container id so we can reference it from later events + # without needing a mid-flow projection. Containers use AUTOINCREMENT-style + # rowid, so MAX(id)+1 is safe within this single-writer transaction. + next_container_row = conn.execute( + "SELECT COALESCE(MAX(id), 0) + 1 FROM containers" + ).fetchone() + container_id = next_container_row[0] + + # 1. chat_created + append_event( + conn, + kind="chat_created", + payload={ + "id": chat_id, + "host_bot_id": bot_id, + "initial_time": initial_time_iso, + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + + # 2. container_created + append_event( + conn, + kind="container_created", + payload={ + "chat_id": chat_id, + "name": container_name, + "type": container_type, + "properties": _parse_properties(container_properties), + "parent_id": None, + }, + ) + + you_interruptible = bool(you_activity_action_interruptible) + bot_interruptible = bool(bot_activity_action_interruptible) + + # 3. activity_change for "you" + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": "you", + "container_id": container_id, + "posture": you_activity_posture, + "action": { + "verb": you_activity_action_verb, + "interruptible": you_interruptible, + "required_attention": you_activity_action_required_attention, + "expected_duration": you_activity_action_expected_duration, + "started_at": initial_time_iso, + }, + "attention": you_activity_attention, + "holding": _parse_holding(you_activity_holding), + "status": {}, + }, + ) + + # 4. activity_change for bot + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": bot_id, + "container_id": container_id, + "posture": bot_activity_posture, + "action": { + "verb": bot_activity_action_verb, + "interruptible": bot_interruptible, + "required_attention": bot_activity_action_required_attention, + "expected_duration": bot_activity_action_expected_duration, + "started_at": initial_time_iso, + }, + "attention": bot_activity_attention, + "holding": _parse_holding(bot_activity_holding), + "status": {}, + }, + ) + + # 5. scene_opened + append_event( + conn, + kind="scene_opened", + payload={ + "chat_id": chat_id, + "container_id": container_id, + "started_at": initial_time_iso, + "participants": ["you", bot_id], + }, + ) + + # 6. edge_update (seed). The seed summary is preserved as the first + # knowledge fact prefixed with ``[summary] `` — proper summary writes happen + # at scene-close (T27). + facts = _parse_facts(edge_seed_knowledge_facts) + if edge_seed_summary.strip(): + facts.insert(0, f"[summary] {edge_seed_summary.strip()}") + append_event( + conn, + kind="edge_update", + payload={ + "source_id": bot_id, + "target_id": "you", + "chat_id": chat_id, + "knowledge_facts": facts, + }, + ) + + # Project all events at once. ``bot_authored`` (already in log from prior + # POST) is idempotent (INSERT OR REPLACE); the new events project cleanly + # because they're being applied for the first time. + project(conn) + + return RedirectResponse(url=f"/chats/{chat_id}", status_code=303) diff --git a/chat/web/middleware.py b/chat/web/middleware.py new file mode 100644 index 0000000..0d4cb05 --- /dev/null +++ b/chat/web/middleware.py @@ -0,0 +1,61 @@ +from __future__ import annotations + +from fastapi import Request +from fastapi.responses import RedirectResponse +from starlette.middleware.base import BaseHTTPMiddleware + +from chat.db.connection import open_db +from chat.state.entities import get_you, list_bots + + +class FirstRunRedirectMiddleware(BaseHTTPMiddleware): + """Redirect users through the first-run flow (per requirements §16.2). + + Behavior on GET requests to landing routes (``/`` and ``/chats``): + + - No ``you_entity`` → ``/settings`` + - ``you_entity`` exists but no bots → ``/bots/new`` + - Otherwise pass through to the underlying handler. + + The middleware is a no-op for: + + - Non-GET requests (POST/PUT writes proceed and surface their own errors). + - Static assets, health checks, and any path under ``/settings``, + ``/bots``, ``/api``, ``/health``, ``/favicon`` — so the user can + actually complete setup once redirected. + - Sub-paths of ``/chats`` (e.g. ``/chats/``, ``/chats//drawer``); + only the bare landing pages get the redirect treatment. Sub-resources + either 404 cleanly or are HTMX partials that should not page-redirect. + """ + + SKIP_PREFIXES = ( + "/static", + "/settings", + "/bots", + "/health", + "/favicon", + "/api", + ) + + async def dispatch(self, request: Request, call_next): + if request.method != "GET": + return await call_next(request) + + path = request.url.path + if any(path.startswith(p) for p in self.SKIP_PREFIXES): + return await call_next(request) + + # Only fire on the landing routes themselves. + if path != "/" and path != "/chats": + return await call_next(request) + + settings = request.app.state.settings + with open_db(settings.db_path) as conn: + you = get_you(conn) + bots = list_bots(conn) + + if you is None: + return RedirectResponse(url="/settings", status_code=303) + if not bots: + return RedirectResponse(url="/bots/new", status_code=303) + return await call_next(request) diff --git a/chat/web/nav.py b/chat/web/nav.py new file mode 100644 index 0000000..842f2e0 --- /dev/null +++ b/chat/web/nav.py @@ -0,0 +1,34 @@ +from __future__ import annotations +from pathlib import Path +from fastapi import APIRouter, Depends, Request +from fastapi.responses import HTMLResponse, RedirectResponse +from fastapi.templating import Jinja2Templates + +from chat.web.bots import get_conn +from chat.state.world import list_chats +from chat.state.entities import get_bot + +TEMPLATES = Jinja2Templates(directory=str(Path(__file__).resolve().parent.parent / "templates")) + +router = APIRouter() + + +@router.get("/", include_in_schema=False) +async def home(): + return RedirectResponse(url="/chats", status_code=303) + + +@router.get("/chats", response_class=HTMLResponse) +async def chats_list(request: Request, conn=Depends(get_conn)): + chats = list_chats(conn) + # Annotate each chat with the host bot's name for display. + for ch in chats: + bot = get_bot(conn, ch["host_bot_id"]) + ch["host_bot_name"] = bot["name"] if bot else ch["host_bot_id"] + # Last-message snippet and last-played-at are blank in v1; T19 fills them. + ch["last_message_snippet"] = "" + ch["last_played_at"] = None + return TEMPLATES.TemplateResponse(request, "chat_list.html", { + "chats": chats, + "active_nav": "chats", + }) diff --git a/chat/web/pubsub.py b/chat/web/pubsub.py new file mode 100644 index 0000000..533c975 --- /dev/null +++ b/chat/web/pubsub.py @@ -0,0 +1,60 @@ +"""In-process per-chat broadcast channel. + +Each ``chat_id`` has a list of subscriber ``asyncio.Queue`` instances. T16 +provides only the registry and fan-out mechanism; T19+ will publish events +(turn appends, streamed tokens, drawer updates, scene close, edge updates) +through this channel so all browser tabs viewing a chat stay in sync. + +The registry is process-local: appropriate for a single-user local server. +""" + +from __future__ import annotations + +import asyncio +from collections import defaultdict +from typing import Any + +# {chat_id: [queue, queue, ...]} +_subscribers: dict[str, list[asyncio.Queue]] = defaultdict(list) +_lock = asyncio.Lock() + + +async def subscribe(chat_id: str) -> asyncio.Queue: + """Subscribe to a chat's broadcast channel. + + Returns a fresh ``asyncio.Queue`` that will receive every event published + to ``chat_id`` while the subscription is active. Callers must invoke + :func:`unsubscribe` when finished (typically on client disconnect) to + avoid leaking queues into the registry. + """ + queue: asyncio.Queue = asyncio.Queue() + async with _lock: + _subscribers[chat_id].append(queue) + return queue + + +async def unsubscribe(chat_id: str, queue: asyncio.Queue) -> None: + """Remove ``queue`` from the registry; remove the chat key if empty.""" + async with _lock: + if chat_id in _subscribers: + if queue in _subscribers[chat_id]: + _subscribers[chat_id].remove(queue) + if not _subscribers[chat_id]: + del _subscribers[chat_id] + + +async def publish(chat_id: str, event: dict[str, Any]) -> None: + """Fan-out ``event`` to every subscriber of ``chat_id``. + + The same dict reference is enqueued to all subscribers. Callers should + treat published events as immutable. Queues are unbounded for v1. + """ + async with _lock: + queues = list(_subscribers.get(chat_id, [])) + for q in queues: + await q.put(event) + + +def subscriber_count(chat_id: str) -> int: + """Test helper. Returns the number of active subscribers for a chat.""" + return len(_subscribers.get(chat_id, [])) diff --git a/chat/web/render.py b/chat/web/render.py new file mode 100644 index 0000000..6a2a286 --- /dev/null +++ b/chat/web/render.py @@ -0,0 +1,106 @@ +"""Transcript display formatting (Task 33, Requirements §16.3). + +Bot and user prose is rendered with **lightweight markdown**: + +* ``*action*`` → ``…`` — italic narration. +* ``**bold**`` → ``…`` — emphasis. +* ``((ooc))`` → ``((ooc))`` — author-to-system + asides; visible to the reader, dimmed/italic in CSS, and stripped from + the prompt sent to the bot (see :func:`chat.web.turns._strip_ooc_for_prompt`). +* ``> line`` → ``

line
``. +* Double newline → paragraph break. +* Everything else is HTML-escaped and wrapped in ``

…

``. + +No headings, code blocks, links, images, or tables — out of scope per +Requirements §16.3. The renderer is the single source of truth used by +both the chat-detail GET (initial timeline render, via Jinja filter) and +the per-turn SSE fragments emitted from :mod:`chat.web.turns`. + +Order of operations matters: + +1. ``html.escape`` the whole input first — every replacement below assumes + user-supplied ``<``/``>``/``&`` are already neutralised, so the wrapper + tags we add can never collide with an attacker-controlled tag. +2. OOC wrap before action/bold so its inner ``*`` are not interpreted. +3. Bold (``**``) before action (``*``) — the bold pattern is stricter and + would otherwise be partially consumed by the action regex. +4. Blockquote pass over already-escaped lines (so we match ``>``). +5. Paragraph split on double newline. +""" + +from __future__ import annotations + +import html +import re + +# ``((…))`` — non-greedy, allows newlines so a multi-line OOC aside still +# wraps cleanly. The inner ``[^)]*?`` keeps it from spanning across a +# closing-paren boundary. +_OOC_PATTERN = re.compile(r"\(\([^)]*?\)\)", re.DOTALL) + +# ``**bold**`` — strict: no embedded asterisks or newlines. Must run +# *before* the single-asterisk action pattern, otherwise ``**x**`` would +# be partly consumed by ``*…*``. +_BOLD_PATTERN = re.compile(r"\*\*([^*\n]+)\*\*") + +# ``*action*`` — single-asterisk italics; same restriction as bold. +_ACTION_PATTERN = re.compile(r"\*([^*\n]+)\*") + +# ``> line`` at start of a line — note we match the *escaped* form +# ``>`` because this pass runs after ``html.escape``. +_BLOCKQUOTE_PATTERN = re.compile(r"^>\s?(.+)$", re.MULTILINE) + + +def render_prose(text: str) -> str: + """Render prose to safe HTML. + + Returns an empty string for empty/whitespace-only input so the caller + can append the result without producing stray ``

`` tags. + """ + if not text or not text.strip(): + return "" + + # Normalise CRLF so paragraph splitting on ``\n\n`` works for input + # pasted from Windows clients. + text = text.replace("\r\n", "\n").replace("\r", "\n") + + escaped = html.escape(text) + + # OOC first — the wrapped span survives subsequent passes. + escaped = _OOC_PATTERN.sub( + lambda m: f'{m.group(0)}', escaped + ) + + # Bold strictly before action (regex precedence — see module docstring). + escaped = _BOLD_PATTERN.sub(r"\1", escaped) + escaped = _ACTION_PATTERN.sub(r'\1', escaped) + + # Blockquote on already-escaped ``>`` markers. + escaped = _BLOCKQUOTE_PATTERN.sub(r"
\1
", escaped) + + # Paragraph splitting — drop empty fragments so a trailing ``\n\n`` + # doesn't yield an empty ``

`` block. + paragraphs = [p.strip() for p in escaped.split("\n\n") if p.strip()] + return "".join(f"

{p}

" for p in paragraphs) + + +def render_turn_html(speaker: str, text: str, role: str = "bot") -> str: + """Render a full transcript turn as ``
…
``. + + Used by both the SSE fragment publisher in :mod:`chat.web.turns` + (per-turn live updates) and indirectly by the chat-detail Jinja + template (initial render, via the ``render_prose`` filter). + + ``role`` selects the CSS class (``turn-you`` vs ``turn-bot``); the + speaker label and role name are HTML-escaped defensively even though + they currently come from trusted server-side state. + """ + speaker_html = html.escape(speaker) + role_html = html.escape(role) + body_html = render_prose(text) + return ( + f'
' + f"{speaker_html}" + f"{body_html}" + f"
" + ) diff --git a/chat/web/settings.py b/chat/web/settings.py new file mode 100644 index 0000000..8256843 --- /dev/null +++ b/chat/web/settings.py @@ -0,0 +1,50 @@ +from __future__ import annotations +from pathlib import Path +from fastapi import APIRouter, Depends, Form, HTTPException, Request +from fastapi.responses import HTMLResponse +from fastapi.templating import Jinja2Templates + +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.state.entities import get_you +from chat.web.bots import get_conn + +TEMPLATES = Jinja2Templates(directory=str(Path(__file__).resolve().parent.parent / "templates")) + +router = APIRouter() + + +@router.get("/settings", response_class=HTMLResponse) +async def settings_get(request: Request, conn=Depends(get_conn)): + you = get_you(conn) or {"name": "", "pronouns": "", "persona": ""} + return TEMPLATES.TemplateResponse( + request, + "settings.html", + {"values": you, "saved": False, "active_nav": "settings"}, + ) + + +@router.post("/settings", response_class=HTMLResponse) +async def settings_post( + request: Request, + name: str = Form(""), + pronouns: str = Form(""), + persona: str = Form(""), + conn=Depends(get_conn), +): + if not name.strip(): + raise HTTPException(status_code=400, detail="name is required") + + payload = { + "name": name.strip(), + "pronouns": pronouns.strip(), + "persona": persona.strip(), + } + append_event(conn, kind="you_authored", payload=payload) + project(conn) + + return TEMPLATES.TemplateResponse( + request, + "settings.html", + {"values": payload, "saved": True, "active_nav": "settings"}, + ) diff --git a/chat/web/sse.py b/chat/web/sse.py new file mode 100644 index 0000000..2b657b9 --- /dev/null +++ b/chat/web/sse.py @@ -0,0 +1,88 @@ +"""Server-Sent Events endpoint for per-chat live updates. + +Each browser tab on ``/chats/`` opens an SSE connection here. On connect: + +1. We verify the chat exists (404 otherwise). +2. We subscribe to the chat's pub/sub channel. +3. We emit a ``snapshot`` event with the current state. T16 only provides a + stub payload (``{"chat_id": , "ready": true}``) so the client can + confirm the channel is live; T19+ will populate it with real state. +4. We loop, awaiting events from the queue and yielding them as SSE frames. + A 15-second keepalive comment is emitted on idle to defeat intermediary + timeouts. +5. When the client disconnects we unsubscribe so the registry doesn't leak. +""" + +from __future__ import annotations + +import asyncio +import json + +from fastapi import APIRouter, Depends, HTTPException, Request +from fastapi.responses import StreamingResponse + +from chat.state.world import get_chat +from chat.web.bots import get_conn +from chat.web.pubsub import subscribe, unsubscribe + +router = APIRouter() + +# Heartbeat cadence. Long enough to avoid chattiness; short enough that most +# HTTP intermediaries won't close an idle connection. +_KEEPALIVE_SECONDS = 15.0 + + +def _format_sse(event: str, data: dict | str) -> bytes: + """Format a single SSE frame: ``event: \\ndata: \\n\\n``. + + ``data`` may be a dict (JSON-serialized) or a raw string. The string + form is used for HTMX SSE swaps where the payload is an HTML + fragment that the client splices into the DOM verbatim. + """ + if isinstance(data, str): + payload = data + else: + payload = json.dumps(data) + return f"event: {event}\ndata: {payload}\n\n".encode("utf-8") + + +@router.get("/chats/{chat_id}/events") +async def chat_events(chat_id: str, request: Request, conn=Depends(get_conn)): + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail="chat not found") + + async def stream(): + queue = await subscribe(chat_id) + try: + # Initial snapshot — T19 will fill in real state. + yield _format_sse("snapshot", {"chat_id": chat_id, "ready": True}) + while True: + if await request.is_disconnected(): + break + try: + event = await asyncio.wait_for( + queue.get(), timeout=_KEEPALIVE_SECONDS + ) + except asyncio.TimeoutError: + # SSE comment line (per spec, lines starting with ":" are + # ignored by the client) — keeps the connection warm. + yield b": keepalive\n\n" + continue + # Allow publishers to set the SSE event name via "event" key; + # default to "message" if omitted. When the remaining payload + # is a single ``data`` string, send it verbatim — that lets + # turn-flow publishers ship pre-rendered HTML fragments that + # HTMX's SSE extension can swap into the DOM directly. + event = dict(event) # don't mutate the published dict + kind = event.pop("event", "message") + if set(event.keys()) == {"data"} and isinstance( + event["data"], str + ): + yield _format_sse(kind, event["data"]) + else: + yield _format_sse(kind, event) + finally: + await unsubscribe(chat_id, queue) + + return StreamingResponse(stream(), media_type="text/event-stream") diff --git a/chat/web/turns.py b/chat/web/turns.py new file mode 100644 index 0000000..894dc72 --- /dev/null +++ b/chat/web/turns.py @@ -0,0 +1,582 @@ +"""POST ``/chats//turns`` — narrative turn flow with SSE streaming. + +The turn flow strings together the pieces built in T17 (turn parser), T18 +(prompt assembler), and T16 (SSE channel): + +1. Parse the user's prose with the classifier into typed segments. +2. Append a ``user_turn`` event capturing both the original prose and the + parsed segments. +3. Append a placeholder ``assistant_turn_started`` marker so observers know + a response is in flight. +4. Build the narrative prompt, dropping OOC segments before they reach the + bot (per Requirements §6.1 the OOC convention is for the author to talk + to the system, not to the in-fiction bot). +5. Stream tokens from the LLM, broadcasting each chunk over the chat's SSE + channel as a ``token`` event so any subscribed browser tab sees them + arrive in real time. +6. On stream complete, append an ``assistant_turn`` event with the full + text and ``truncated=False``. Then run a post-turn state-update pass + (Requirements §3.4): one classifier call per directed edge between + present entities, each producing an ``edge_update`` event with + affinity/trust/knowledge deltas. Finally publish a ``turn_html`` + event with a ready-to-swap HTML fragment so HTMX's SSE extension can + append it to the timeline without a page reload. +7. Return ``204 No Content`` — the SSE channel is the real conveyor of + state, not the POST response body. + +Errors during streaming flip the assistant_turn's ``truncated`` flag to +``True`` and we still commit what we received. ``asyncio.CancelledError`` +is treated identically and re-raised after recording the partial turn. +""" + +from __future__ import annotations + +import asyncio +import html +import json + +from fastapi import APIRouter, Depends, Form, HTTPException, Request +from fastapi.responses import HTMLResponse, RedirectResponse, Response + +from chat.eventlog.log import append_and_apply, append_event +from chat.services.background import SignificanceJob +from chat.services.memory_write import record_turn_memory +from chat.services.prompt import assemble_narrative_prompt +from chat.services.rewind import compute_rewind_preview, execute_rewind +from chat.services.scene_close import detect_scene_close +from chat.services.scene_summarize import apply_scene_close_summary +from chat.services.state_update import compute_state_update +from chat.services.turn_parse import ParsedTurn, parse_turn +from chat.state.edges import get_edge +from chat.state.entities import get_bot, get_you +from chat.state.world import active_scene, get_chat, get_container +from chat.web.bots import get_conn +from chat.web.kickoff import get_llm_client +from chat.web.pubsub import publish +from chat.web.render import render_turn_html as _render_turn_html + +router = APIRouter() + + +# Module-level registry of in-flight streaming tasks, keyed by chat_id. +# The POST /chats//turns/cancel route looks up the task and calls +# .cancel(); the streaming coroutine in post_turn catches the resulting +# CancelledError, commits the partial as truncated, and unregisters. +# Single-process v1 only — sufficient for one user with multiple tabs. +_in_flight_tasks: dict[str, asyncio.Task] = {} + + +def _strip_ooc_for_prompt(parsed: ParsedTurn) -> str: + """Concatenate non-OOC segments back to a prose string for the prompt. + + OOC segments (``((double parens))``) are kept in the user_turn payload + for transcript display but stripped before assembly so the bot never + sees author-to-system messages. + """ + keep = [s.text for s in parsed.segments if s.kind != "ooc"] + return " ".join(keep).strip() + + +def _read_recent_dialogue(conn, chat_id: str, limit: int = 200) -> list[dict]: + """Return user-side and assistant_turn events for ``chat_id``. + + Includes ``user_turn``, ``user_turn_edit`` (T29 edited prose), and + ``assistant_turn``. Ordered oldest-first; superseded/hidden rows are + skipped so regenerated turns (T29) drop out of the rendered timeline. + Each entry is shaped ``{"speaker": , "text": }`` + for the prompt assembler and the chat-detail template. + """ + cur = conn.execute( + "SELECT id, kind, payload_json FROM event_log " + "WHERE kind IN ('user_turn', 'user_turn_edit', 'assistant_turn') " + " AND superseded_by IS NULL AND hidden = 0 " + "ORDER BY id DESC LIMIT ?", + (limit,), + ) + rows = cur.fetchall() + rows.reverse() # back to chronological order + out: list[dict] = [] + for _row_id, kind, payload_json in rows: + p = json.loads(payload_json) + if p.get("chat_id") != chat_id: + continue + if kind in ("user_turn", "user_turn_edit"): + # Edited prose substitutes for the original user_turn (the + # original is marked superseded_by and filtered above). + out.append({"speaker": "you", "text": p.get("prose", "")}) + else: + out.append( + { + "speaker": p.get("speaker_id", "bot"), + "text": p.get("text", ""), + } + ) + return out + + +@router.post("/chats/{chat_id}/turns") +async def post_turn( + chat_id: str, + request: Request, + prose: str = Form(""), + conn=Depends(get_conn), + client=Depends(get_llm_client), +): + if not prose.strip(): + raise HTTPException(status_code=400, detail="prose cannot be empty") + + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + + host_bot = get_bot(conn, chat["host_bot_id"]) + if host_bot is None: + # Defensive: chat row references a missing bot. + raise HTTPException( + status_code=404, + detail=f"host bot not found: {chat['host_bot_id']}", + ) + + settings = request.app.state.settings + + # 1. Parse turn (classifier). + parsed = await parse_turn( + client, model=settings.classifier_model, prose=prose + ) + prompt_prose = _strip_ooc_for_prompt(parsed) + + # 2. Append user_turn event. + user_turn_event_id = append_event( + conn, + kind="user_turn", + payload={ + "chat_id": chat_id, + "prose": prose, + "segments": [s.model_dump() for s in parsed.segments], + }, + ) + + # 3. Append assistant_turn_started placeholder. ``user_turn``, + # ``assistant_turn_started``, and ``assistant_turn`` have no registered + # projector handlers — they live in the event_log purely for transcript + # rendering — so we don't call ``project`` here. (Re-projecting now would + # also re-run prior non-idempotent inserts like ``chat_created``.) + append_event( + conn, + kind="assistant_turn_started", + payload={ + "chat_id": chat_id, + "speaker_id": host_bot["id"], + "user_turn_id": user_turn_event_id, + }, + ) + + # 4. Build the narrative prompt. + recent = _read_recent_dialogue(conn, chat_id, limit=20) + # Drop the just-appended user turn from ``recent`` — it's passed as + # ``user_turn_prose`` to the assembler and would otherwise duplicate. + if recent and recent[-1].get("speaker") == "you": + recent = recent[:-1] + messages = assemble_narrative_prompt( + conn, + chat_id=chat_id, + speaker_bot_id=host_bot["id"], + user_turn_prose=prompt_prose if prompt_prose else None, + recent_dialogue=recent, + budget_soft=settings.narrative_budget_soft, + budget_hard=settings.narrative_budget_hard, + ) + + # 5. Stream and accumulate tokens. The stream runs as a Task so the + # /turns/cancel route can invoke ``Task.cancel()`` to abort it + # mid-stream. ``accumulated`` is a closure over the inner coroutine, + # so when the await on ``stream_task`` raises CancelledError below + # we still see whatever tokens were appended before cancellation. + accumulated: list[str] = [] + truncated = False + cancelled = False + + async def _stream() -> None: + async for chunk in client.stream( + messages, + model=settings.narrative_model, + max_tokens=settings.narrative_max_tokens, + temperature=settings.narrative_temperature, + ): + accumulated.append(chunk) + await publish( + chat_id, + { + "event": "token", + "text": chunk, + "speaker_id": host_bot["id"], + }, + ) + + stream_task = asyncio.create_task(_stream()) + _in_flight_tasks[chat_id] = stream_task + try: + await stream_task + except asyncio.CancelledError: + # Preserve the partial output before letting the cancellation + # propagate so the transcript reflects what the user actually saw. + truncated = True + cancelled = True + except Exception: + # Surface as a truncated turn rather than losing the partial output. + truncated = True + finally: + # Always unregister so a subsequent turn can register a fresh task. + _in_flight_tasks.pop(chat_id, None) + + full_text = "".join(accumulated) + + # 6. Append the assistant_turn with the final text. (See note above on + # why we skip ``project`` for these transcript-only event kinds.) + append_event( + conn, + kind="assistant_turn", + payload={ + "chat_id": chat_id, + "speaker_id": host_bot["id"], + "text": full_text, + "truncated": truncated, + "user_turn_id": user_turn_event_id, + }, + ) + + # 6a. Per-turn memory write (Plan §11.1, T21). Phase 1 single-bot: + # only the host bot has a memory store, witness flags are + # ``[you=1, host=1, guest=0]``, and ``pov_summary`` is the raw + # narrative text (T27 will rewrite at scene close). Significance + # defaults to 1; T22's async classifier pass will overwrite it. + scene = active_scene(conn, chat_id) + _event_id, memory_id = record_turn_memory( + conn, + chat_id=chat_id, + host_bot_id=host_bot["id"], + narrative_text=full_text, + scene_id=scene["id"] if scene else None, + chat_clock_at=chat.get("time"), + ) + + # 6b. Post-turn state-update pass (Requirements §3.4). For Phase 1 + # the only present entities are ``you`` and ``host_bot`` so we run + # two classifier calls — one per directed edge — and append the + # resulting ``edge_update`` events. The recent-dialogue slice is + # re-read here so the pass sees the just-appended assistant turn. + # We use ``append_and_apply`` (vs append + project) because the + # edge_update handler is *not* replay-safe: re-projecting prior + # events would re-apply their deltas on top of the live row. + recent_for_update = _read_recent_dialogue(conn, chat_id, limit=10) + you_entity = get_you(conn) or {"name": "you", "persona": ""} + last_at = chat.get("time") + + edge_b2y = get_edge(conn, host_bot["id"], "you") or { + "affinity": 50, + "trust": 50, + "summary": "", + } + update_b2y = await compute_state_update( + client, + model=settings.classifier_model, + source_id=host_bot["id"], + target_id="you", + source_name=host_bot["name"], + source_persona=host_bot.get("persona", ""), + target_name=you_entity.get("name", "you"), + prior_affinity=edge_b2y["affinity"], + prior_trust=edge_b2y["trust"], + prior_summary=edge_b2y.get("summary", "") or "", + recent_dialogue=recent_for_update, + ) + append_and_apply( + conn, + kind="edge_update", + payload={ + "source_id": host_bot["id"], + "target_id": "you", + "chat_id": chat_id, + "affinity_delta": update_b2y.affinity_delta, + "trust_delta": update_b2y.trust_delta, + "knowledge_facts": update_b2y.knowledge_facts, + "last_interaction_at": last_at, + "last_interaction_chat_id": chat_id, + }, + ) + + edge_y2b = get_edge(conn, "you", host_bot["id"]) or { + "affinity": 50, + "trust": 50, + "summary": "", + } + update_y2b = await compute_state_update( + client, + model=settings.classifier_model, + source_id="you", + target_id=host_bot["id"], + source_name=you_entity.get("name", "you"), + source_persona=you_entity.get("persona", "") or "", + target_name=host_bot["name"], + prior_affinity=edge_y2b["affinity"], + prior_trust=edge_y2b["trust"], + prior_summary=edge_y2b.get("summary", "") or "", + recent_dialogue=recent_for_update, + ) + append_and_apply( + conn, + kind="edge_update", + payload={ + "source_id": "you", + "target_id": host_bot["id"], + "chat_id": chat_id, + "affinity_delta": update_y2b.affinity_delta, + "trust_delta": update_y2b.trust_delta, + "knowledge_facts": update_y2b.knowledge_facts, + "last_interaction_at": last_at, + "last_interaction_chat_id": chat_id, + }, + ) + + # 6c. Enqueue the async significance pass (Plan §11.1, T22). The + # worker scores the just-written memory 0-3, updates significance, + # and auto-pins on score 3 with the §8.5 soft-cap eviction rule. + # Enqueued before the broadcast so it's outstanding by the time the + # client sees ``turn_html`` — but the worker is async, so the user + # never blocks on it. + worker = getattr(request.app.state, "background_worker", None) + if worker is not None and memory_id is not None: + worker.enqueue( + SignificanceJob( + memory_id=memory_id, + narrative_text=full_text, + prior_dialogue=recent_for_update, + host_bot_id=host_bot["id"], + ) + ) + + # 6d. Scene-close detection (Plan §7.2, T26). Runs AFTER assistant_turn + # so the bot's response is the closing scene's final beat — closing + # before narrative would force the bot to speak "in no scene", which + # is awkward. Hard signals only in Phase 1: container change parsed + # from prose, or explicit "fade out" / "we're done here" patterns. + # On classifier failure the service returns ``should_close=False`` + # so the turn flow keeps moving; the manual close button in the + # drawer is the always-available fallback. + # + # Skip empty prose — no signal to classify and no point spending a + # round-trip. Skip when there's no active scene (e.g. after a prior + # close in the same chat) — we have nothing to close. T13 (kickoff) + # is the only scene-opener path in v1; Phase 2-3 will handle + # automatic re-opening with the next container. + if scene is not None and prose.strip(): + container = None + if scene.get("container_id") is not None: + container = get_container(conn, scene["container_id"]) + container_name = container["name"] if container else "unknown" + decision = await detect_scene_close( + client, + model=settings.classifier_model, + prose=prose, + current_container_name=container_name, + ) + if decision.should_close: + append_and_apply( + conn, + kind="scene_closed", + payload={ + "scene_id": scene["id"], + "ended_at": chat.get("time"), + # T27 promotes the per-POV summary into ``edges.summary`` + # but doesn't currently set scene significance — the + # async significance pass (T22) operates on memories. + "significance": 0, + }, + ) + # T27: per-POV summary + edge summary update + knowledge + # promotion. Runs synchronously after the close so the + # next turn (or a subsequent GET /chats/) sees the + # rewritten memories and edge summary. Tolerates classifier + # failure (returns the empty default and skips the writes). + await apply_scene_close_summary( + conn, + client, + classifier_model=settings.classifier_model, + chat_id=chat_id, + scene_id=scene["id"], + host_bot_id=host_bot["id"], + timeout_s=settings.classifier_timeout_s, + ) + + # 7. Broadcast a JSON completion event (for JS consumers) and an HTML + # fragment event (for HTMX SSE swap-into-timeline). + await publish( + chat_id, + { + "event": "assistant_turn_complete", + "speaker_id": host_bot["id"], + "text": full_text, + "truncated": truncated, + }, + ) + assistant_html = _render_turn_html( + host_bot["name"], full_text, role="bot" + ) + await publish( + chat_id, {"event": "turn_html", "data": assistant_html} + ) + + if cancelled: + # Re-raise after the partial-turn has been recorded. + raise asyncio.CancelledError + + return Response(status_code=204) + + +# --------------------------------------------------------------------------- +# Cancel route (Task 34). +# +# Fire-and-forget: the Stop button POSTs here, we mark the in-flight +# streaming Task as cancelled, and return 204 immediately. The cancel +# propagates into the streaming coroutine on its next await, the +# CancelledError handler in ``post_turn`` catches it, and the partial +# is committed with ``truncated=True``. No body is needed — the SSE +# channel is the conveyor of state. If no turn is in flight (or the +# task already completed), we 204 silently so the client can fire the +# Stop button without a precondition check. +# --------------------------------------------------------------------------- + + +@router.post("/chats/{chat_id}/turns/cancel") +async def cancel_turn(chat_id: str, request: Request): + task = _in_flight_tasks.get(chat_id) + if task is None or task.done(): + return Response(status_code=204) + task.cancel() + return Response(status_code=204) + + +# --------------------------------------------------------------------------- +# Rewind routes (Task 28). +# +# Two endpoints: a GET that renders the impact-preview modal, and a POST +# that actually executes the rewind. The execution path opens its own +# database connection because the route's ``conn`` is closed when the +# dependency-injection scope exits — passing it to ``execute_rewind`` +# would dangle. +# --------------------------------------------------------------------------- + + +@router.get( + "/chats/{chat_id}/rewind/preview/{event_id}", + response_class=HTMLResponse, +) +async def rewind_preview( + chat_id: str, + event_id: int, + request: Request, + conn=Depends(get_conn), +): + """Render the rewind impact-preview modal as a small HTML fragment. + + The HTMX form inside the fragment posts to the execute endpoint + below. v1 keeps the markup minimal — Task 35 polishes the modal. + """ + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + preview = compute_rewind_preview(conn, event_id) + items = "".join( + f"
  • {count} × {html.escape(kind)}
    • " + for kind, count in preview["by_kind"].items() + ) + body = ( + "
    " + f"

    Rewind to event {event_id}?

    " + f"

    This will remove {preview['total_events']} events:

    " + f"
      {items}
    " + f"
    " + "" + "
    " + "
    " + ) + return HTMLResponse(body) + + +# --------------------------------------------------------------------------- +# Regenerate route (Task 29). +# +# A POST that re-streams the most recent assistant turn. The prior +# ``assistant_turn`` event is kept in the log but flagged +# ``superseded_by`` so the timeline filter in :func:`_read_recent_dialogue` +# hides it. When the user supplies ``prose`` the original ``user_turn`` +# is also superseded by a fresh ``user_turn_edit`` event capturing the +# edit. Significance is *not* re-run on regenerate (per plan §11.1) but +# state-update + memory writes are. +# --------------------------------------------------------------------------- + + +@router.post("/chats/{chat_id}/turns/{event_id}/regenerate") +async def regenerate_turn( + chat_id: str, + event_id: int, + request: Request, + prose: str | None = Form(None), + conn=Depends(get_conn), + client=Depends(get_llm_client), +): + """Regenerate the assistant turn referenced by ``event_id``. + + ``prose`` is optional. When provided (and non-empty) we capture a + ``user_turn_edit`` event before re-streaming. Returns 204 on + success, 404 when the chat or assistant_turn event is missing. The + SSE channel emits per-token events as the new text arrives. + """ + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + settings = request.app.state.settings + # Local import keeps the module import graph flat (the service + # imports from ``state`` / ``services`` siblings already). + from chat.services.regenerate import regenerate_assistant_turn + + edited_prose = prose if prose else None + try: + await regenerate_assistant_turn( + conn, + client, + settings=settings, + chat_id=chat_id, + original_assistant_event_id=event_id, + edited_user_prose=edited_prose, + ) + except ValueError as e: + raise HTTPException(status_code=404, detail=str(e)) + return Response(status_code=204) + + +@router.post("/chats/{chat_id}/rewind/{event_id}") +async def rewind_execute( + chat_id: str, + event_id: int, + request: Request, + conn=Depends(get_conn), +): + """Execute the rewind: snapshot, truncate event_log, re-project. + + Note: ``conn`` is only used to validate the chat exists. The actual + rewind opens its own connection inside ``execute_rewind`` because + we need it to commit independently and survive the route's + dependency teardown. + """ + chat = get_chat(conn, chat_id) + if chat is None: + raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}") + settings = request.app.state.settings + execute_rewind( + db_path=settings.db_path, + data_dir=settings.data_dir, + after_event_id=event_id, + ) + return RedirectResponse(url=f"/chats/{chat_id}", status_code=303) diff --git a/data/config.example.toml b/data/config.example.toml new file mode 100644 index 0000000..1da91f2 --- /dev/null +++ b/data/config.example.toml @@ -0,0 +1,6 @@ +# Copy this file to data/config.toml and fill in your API key. +featherless_api_key = "REPLACE_ME" +narrative_model = "dphn/Dolphin-Mistral-24B-Venice-Edition" +classifier_model = "NousResearch/Hermes-3-Llama-3.1-8B" +ooc_marker = "((" +retrieval_k = 4 diff --git a/docs/plans/2026-04-26-v1-phase1-implementation.md b/docs/plans/2026-04-26-v1-phase1-implementation.md index 1a1ce16..0ad593d 100644 --- a/docs/plans/2026-04-26-v1-phase1-implementation.md +++ b/docs/plans/2026-04-26-v1-phase1-implementation.md @@ -884,7 +884,7 @@ def get_bot(conn: Connection, bot_id: str) -> dict | None: row = conn.execute("SELECT * FROM bots WHERE id = ?", (bot_id,)).fetchone() if not row: return None - cols = [c[0] for c in conn.execute("PRAGMA table_info(bots)").fetchall()] + cols = [c[1] for c in conn.execute("PRAGMA table_info(bots)").fetchall()] d = dict(zip(cols, row)) d["voice_samples"] = json.loads(d.pop("voice_samples_json")) d["traits"] = json.loads(d.pop("traits_json")) diff --git a/docs/plans/2026-04-26-v2-phase2-implementation.md b/docs/plans/2026-04-26-v2-phase2-implementation.md new file mode 100644 index 0000000..211199c --- /dev/null +++ b/docs/plans/2026-04-26-v2-phase2-implementation.md @@ -0,0 +1,910 @@ +# Roleplay Engine — Phase 2 Implementation Plan + +> **For Claude:** REQUIRED SUB-SKILL: Use `superpowers-extended-cc:executing-plans` to implement this plan task-by-task. Use `superpowers-extended-cc:dispatching-parallel-agents` for the parallel waves below. + +**Goal:** Add multi-entity (3-entity) scene support: guest bot can be added to a host's chat; up to 3 entities present simultaneously (you + host + guest); turn flow handles silent witnesses, interjections, per-pair edges, and per-witness memory; drawer reflects guest state; scene close writes per-POV summaries for each present witness. + +**Architecture:** Builds on Phase 1's event-sourced architecture. New event kinds (`guest_added`, `guest_removed`, `group_node_initialized`) carry the multi-entity state changes; existing handlers (`edge_update`, `memory_written`) already accept any `source_id`/`target_id` and witness mask, so most schema work is additive. The "have they met?" first-co-appearance prompt runs once per `(botA, botB)` pair and seeds initial inter-bot edges via existing `edge_update` events. + +**Tech Stack:** Same as Phase 1 (Python 3.11+, FastAPI, HTMX, SQLite, Featherless). No new dependencies. + +**Source-of-truth references:** +- Phase 2 scope: requirements doc §13 "Phase 2 — multi-entity" +- Behavioral details: requirements doc §6.2 (turn-taking with interjection), §7.5 (guest leaves), §8.5 (memory ownership), §11.2 (per-POV summaries on close) +- Conventions: [../../CLAUDE.md](../../CLAUDE.md) §"Behavioral defaults" +- Phase 1 plan (style, TDD pattern): [2026-04-26-v1-phase1-implementation.md](2026-04-26-v1-phase1-implementation.md) + +When a task says "see §X", that's the requirements doc unless stated otherwise. + +--- + +## Pre-flight + +**Branch:** Create `phase-2` from the latest `main` after Phase 1 has been merged. If Phase 1 is still in PR review, branch off `phase-1` directly: + +```bash +# Option A: after main has phase-1 merged +git checkout main && git pull && git checkout -b phase-2 + +# Option B: continue from phase-1 directly +git checkout phase-1 && git pull && git checkout -b phase-2 +``` + +**Schema baseline:** Phase 1 leaves the DB at version 7. Phase 2 adds **0008_group_node.sql**. No other migrations expected. + +**Pinned non-negotiables (carried forward from Phase 1):** +- State changes go through the event log. Use `append_and_apply(conn, kind, payload)` for the live path; `apply_event` only after a fresh `append_event` returning the new id. +- Witness filter every memory read at SQL level (hard `WHERE` constraint; never a soft signal). +- Edges are directed; `botA → botB` and `botB → botA` are independent records. +- Per-POV scene summaries — never write omniscient narration. +- TDD: every task starts with a failing test. +- One commit per task minimum, more if it splits naturally. + +**Verification before claiming done:** Use `superpowers-extended-cc:verification-before-completion` — run the test command, paste actual output. Don't assume green. + +--- + +## Parallel-Execution Strategy + +This plan is structured into **6 waves** of tasks. Within a wave, tasks are designed to touch disjoint files so they can be executed by parallel subagents safely. Between waves, the controller (you, the controlling Claude session) merges each subagent's commits and verifies the suite stays green before dispatching the next wave. + +### How to dispatch a wave in parallel + +Use the **Agent tool with `isolation: "worktree"`** so each subagent gets its own git worktree. The runtime cleans up the worktree automatically if no changes are made; otherwise it returns the path + branch for the controller to merge. + +In a single message, dispatch all tasks in the wave: + +``` +Agent({ + description: "Wave 1 — T36 group_node schema", + subagent_type: "general-purpose", + isolation: "worktree", + prompt: "", +}) +Agent({ + description: "Wave 1 — T37 guest events", + subagent_type: "general-purpose", + isolation: "worktree", + prompt: "", +}) +Agent({ + description: "Wave 1 — T38 relationship-seed service", + subagent_type: "general-purpose", + isolation: "worktree", + prompt: "", +}) +``` + +All three subagents start simultaneously, each working on a private worktree branched off `phase-2`. They cannot see each other's changes (no shared filesystem state) — that's the safety guarantee. + +### After a wave completes + +1. Each subagent returns its worktree path and commit SHA. +2. **Run a spec + quality reviewer subagent on each completed task** (same pattern as Phase 1 — see `superpowers-extended-cc:requesting-code-review`). +3. **Merge the wave into `phase-2`** in any order (file-disjointness guarantees no conflict). Use fast-forward if possible: + + ```bash + git checkout phase-2 + for branch in ; do + git merge --no-ff "$branch" -m "merge: " + done + ``` + +4. **Run the full test suite** on the merged `phase-2`. If it's red, the wave's mutual independence assumption was violated — bisect to find the offending pair, fix, re-merge. +5. **Push `phase-2` to gitea** so the work is durable before the next wave starts. +6. Optionally clean up worktrees: `git worktree remove .worktrees/`. + +### Conflict prevention checklist (apply before dispatch) + +For each parallel wave, verify the **Files** sections of all tasks in that wave have **no overlapping paths**. The waves below are designed to satisfy this; if you decide to add or merge tasks, re-check. + +If a hot file (`chat/web/turns.py`, `chat/services/prompt.py`, `chat/templates/_drawer.html`) needs changes from multiple tasks, do **not** parallelize them — serialize within the wave or split into separate waves. + +### Failure recovery + +If one subagent in a parallel wave fails (test failures, blocked, infinite loop): +- **Do not block the wave on a failure.** Cancel the failed subagent, merge the others' successful work, and re-dispatch the failed task as a single follow-up. +- If a failure exposes a bad assumption shared by multiple tasks (e.g. an event-payload schema mismatch), pause the wave and revisit the plan. + +### Why each wave is parallel-safe + +| Wave | Tasks | Hot files touched | Disjoint? | +|------|-------|-------------------|-----------| +| 1 | T36, T37, T38 | new files only + `chat/state/world.py` (T37 only) | ✅ | +| 2 | T39, T40, T41 | new files only + `chat/services/memory_write.py` (T41 only) | ✅ | +| 3 | T42 | `chat/web/drawer.py`, `chat/templates/_drawer.html` | (single task) | +| 4a | T43, T45 | `chat/services/prompt.py` (T43), `chat/services/scene_summarize.py` (T45) | ✅ | +| 4b | T44 | `chat/web/turns.py`, `chat/services/regenerate.py` | (single task; depends on 4a) | +| 5 | T46, T47, T48 | new tests + `chat/state/entities.py` (T47) + docs (T48) | ✅ | + +--- + +## Task overview + +``` +Wave 1 ─┬─ T36: group_node schema + handler + ├─ T37: guest_added / guest_removed events + └─ T38: relationship-seed service ("have they met?") + +Wave 2 ─┬─ T39: interjection classifier service + ├─ T40: multi-entity state-update coordinator + └─ T41: multi-witness memory write helper + +Wave 3 ─── T42: drawer guest support (add/remove + render guest state) + +Wave 4a ─┬─ T43: multi-entity prompt assembly (extends assemble_narrative_prompt) + └─ T45: multi-entity per-POV summaries on scene close + +Wave 4b ─── T44: multi-entity turn flow integration (post_turn rewrite) + +Wave 5 ─┬─ T46: witness filter test coverage (cross-witness scenarios) + ├─ T47: bot reset cascades to guest scenes + └─ T48: Phase 2 documentation update +``` + +Critical path: 6 sequential merge points. Total tasks: 13. Wall-clock parallelism advantage depends on subagent dispatch overhead, but in principle Wave 1's 3 tasks can run concurrently in ~the time of one task. + +--- + +## Wave 1 — Foundation + +These three tasks are **fully independent**: T36 adds new files only, T37 modifies `chat/state/world.py` (additive event handlers), T38 adds new files only. Dispatch all three in parallel. + +### Task 36: Group node schema + handler + +**Files:** +- Create: `chat/db/migrations/0008_group_node.sql` +- Create: `chat/state/group_node.py` +- Create: `tests/test_group_node.py` + +**Spec:** Adds the `group_node` table (one row per chat, populated when all three entities are present in a scene) and a projector handler for the `group_node_initialized` event. The group node carries the shared summary, group dynamic, inside jokes, and active threads (Phase 3 will populate `active_threads`; for Phase 2, just `summary` and `dynamic` matter). + +**Step 1: Write the failing test** + +```python +# tests/test_group_node.py +from chat.db.migrate import apply_migrations +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.state.group_node import get_group_node +import chat.state.entities # noqa +import chat.state.world # noqa +import chat.state.group_node # noqa: F401 - registers handlers + +def test_group_node_initialized_creates_row(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + # Seed bot, you, chat (minimal world state — no scene yet) + append_event(conn, kind="bot_authored", payload={ + "id": "bot_a", "name": "BotA", "persona": "...", + "voice_samples": [], "traits": [], "backstory": "", + "initial_relationship_to_you": "", "kickoff_prose": "", + }) + append_event(conn, kind="chat_created", payload={ + "id": "chat_bot_a", "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", "weather": "", + }) + append_event(conn, kind="group_node_initialized", payload={ + "chat_id": "chat_bot_a", + "members": ["you", "bot_a", "bot_b"], + "summary": "", + "dynamic": "", + }) + project(conn) + gn = get_group_node(conn, "chat_bot_a") + assert gn is not None + assert gn["members"] == ["you", "bot_a", "bot_b"] + assert gn["summary"] == "" +``` + +**Step 2: Run test to verify it fails** + +```bash +.venv/bin/pytest tests/test_group_node.py -v +``` + +Expected: `ModuleNotFoundError: No module named 'chat.state.group_node'`. + +**Step 3: Write minimal implementation** + +`chat/db/migrations/0008_group_node.sql`: + +```sql +CREATE TABLE group_node ( + chat_id TEXT PRIMARY KEY, + members_json TEXT NOT NULL, + summary TEXT NOT NULL DEFAULT '', + dynamic TEXT NOT NULL DEFAULT '', + threads_json TEXT NOT NULL DEFAULT '[]', + updated_at TEXT NOT NULL DEFAULT (datetime('now')) +); +``` + +`chat/state/group_node.py`: + +```python +from __future__ import annotations +import json +from sqlite3 import Connection +from chat.eventlog.projector import on +from chat.eventlog.log import Event + + +@on("group_node_initialized") +def _apply_group_node_initialized(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "INSERT OR REPLACE INTO group_node " + "(chat_id, members_json, summary, dynamic, threads_json) " + "VALUES (?, ?, ?, ?, ?)", + ( + p["chat_id"], + json.dumps(p["members"]), + p.get("summary", ""), + p.get("dynamic", ""), + json.dumps(p.get("threads", [])), + ), + ) + + +@on("group_node_updated") +def _apply_group_node_updated(conn: Connection, e: Event) -> None: + """T45 calls this on scene close to rewrite summary + dynamic.""" + p = e.payload + conn.execute( + "UPDATE group_node SET summary = ?, dynamic = ?, updated_at = datetime('now') " + "WHERE chat_id = ?", + (p.get("summary", ""), p.get("dynamic", ""), p["chat_id"]), + ) + + +def get_group_node(conn: Connection, chat_id: str) -> dict | None: + row = conn.execute( + "SELECT chat_id, members_json, summary, dynamic, threads_json, updated_at " + "FROM group_node WHERE chat_id = ?", + (chat_id,), + ).fetchone() + if not row: + return None + return { + "chat_id": row[0], + "members": json.loads(row[1]), + "summary": row[2], + "dynamic": row[3], + "threads": json.loads(row[4]), + "updated_at": row[5], + } +``` + +**Step 4: Run test to verify it passes** + +```bash +.venv/bin/pytest tests/test_group_node.py -v +``` + +Expected: 1 passed. + +**Step 5: Commit** + +```bash +git add chat/db/migrations/0008_group_node.sql chat/state/group_node.py tests/test_group_node.py +git commit -m "feat: group_node schema + projector handlers" +``` + +**Notes for the implementer:** +- Add a second test for `group_node_updated`: append init then update, assert `summary` and `dynamic` change but `members` stays. +- Add a test for `get_group_node` returning `None` on a missing chat_id. +- Schema version after migration: 8. The migration runner handles this automatically; no test assertion on schema_version. + +--- + +### Task 37: Guest add / remove events + handlers + +**Files:** +- Modify: `chat/state/world.py` (add `_apply_guest_added`, `_apply_guest_removed` handlers; both update `chats.guest_bot_id`) +- Create: `tests/test_guest_events.py` + +**Spec:** Two new event kinds. +- `guest_added` payload: `{chat_id, guest_bot_id}`. Handler sets `chats.guest_bot_id = ?`. +- `guest_removed` payload: `{chat_id}`. Handler sets `chats.guest_bot_id = NULL`. + +These are pure state mutations — no related side effects. The kickoff parse-and-confirm flow (T13, Phase 1) and the new T39 interjection / T42 drawer routes will append these events. + +**Step 1: Write the failing test** + +```python +# tests/test_guest_events.py +from chat.db.migrate import apply_migrations +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.state.world import get_chat +import chat.state.entities # noqa +import chat.state.world # noqa + + +def test_guest_added_sets_guest_bot_id(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + # Seed bot, chat + append_event(conn, kind="bot_authored", payload={ + "id": "bot_a", "name": "BotA", "persona": "...", + "voice_samples": [], "traits": [], "backstory": "", + "initial_relationship_to_you": "", "kickoff_prose": "", + }) + append_event(conn, kind="bot_authored", payload={ + "id": "bot_b", "name": "BotB", "persona": "...", + "voice_samples": [], "traits": [], "backstory": "", + "initial_relationship_to_you": "", "kickoff_prose": "", + }) + append_event(conn, kind="chat_created", payload={ + "id": "chat_bot_a", "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", "weather": "", + }) + append_event(conn, kind="guest_added", payload={ + "chat_id": "chat_bot_a", "guest_bot_id": "bot_b", + }) + project(conn) + chat = get_chat(conn, "chat_bot_a") + assert chat["guest_bot_id"] == "bot_b" + + +def test_guest_removed_clears_guest_bot_id(tmp_path): + # similar: add then remove, assert guest_bot_id is None + ... +``` + +**Step 3: Implementation** + +In `chat/state/world.py`, add the two handlers next to `_apply_chat_created`: + +```python +@on("guest_added") +def _apply_guest_added(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "UPDATE chats SET guest_bot_id = ? WHERE id = ?", + (p["guest_bot_id"], p["chat_id"]), + ) + + +@on("guest_removed") +def _apply_guest_removed(conn: Connection, e: Event) -> None: + p = e.payload + conn.execute( + "UPDATE chats SET guest_bot_id = NULL WHERE id = ?", + (p["chat_id"],), + ) +``` + +**Step 5: Commit** + +```bash +git add chat/state/world.py tests/test_guest_events.py +git commit -m "feat: guest_added / guest_removed event handlers" +``` + +**Notes:** +- 2 tests minimum (added, removed). Optional third: idempotent re-add (overwrites cleanly). +- Don't add any UI here — T42 handles UI. + +--- + +### Task 38: Relationship-seed service ("have they met?") + +**Files:** +- Create: `chat/services/relationship_seed.py` +- Create: `tests/test_relationship_seed.py` + +**Spec:** Per requirements §5.2: when two bots first co-appear in a chat, prompt the user with "Have they met before? If yes, write a short prose seed describing how." The seed is parsed via classifier into structured `botA ↔ botB` edge content (summary + initial knowledge facts). + +This task adds the **service layer** only. T39 (interjection) doesn't touch this; T42 (drawer guest UI) calls it via a route added there. So at the service level, we just expose: + +```python +async def seed_inter_bot_edges( + client: LLMClient, + *, + classifier_model: str, + bot_a_id: str, + bot_a_name: str, + bot_b_id: str, + bot_b_name: str, + relationship_prose: str, # user-supplied prose; empty = "they haven't met" + timeout_s: float = 30.0, +) -> RelationshipSeed: + """Parse user-supplied prose into structured edge content for both + directed pairs (bot_a → bot_b and bot_b → bot_a). Return the + RelationshipSeed; caller is responsible for emitting two edge_update + events.""" +``` + +`RelationshipSeed`: + +```python +class RelationshipSeed(BaseModel): + a_to_b_summary: str = "" + a_to_b_knowledge_facts: list[str] = Field(default_factory=list) + a_to_b_affinity_delta: int = 0 # signed, -10..+10 typical + a_to_b_trust_delta: int = 0 + b_to_a_summary: str = "" + b_to_a_knowledge_facts: list[str] = Field(default_factory=list) + b_to_a_affinity_delta: int = 0 + b_to_a_trust_delta: int = 0 +``` + +If `relationship_prose` is empty/whitespace, short-circuit and return an empty `RelationshipSeed` (they haven't met → fresh edges with default 50/50). + +**Step 1: Failing test** + +```python +import pytest, json +from chat.llm.mock import MockLLMClient +from chat.services.relationship_seed import seed_inter_bot_edges, RelationshipSeed + + +@pytest.mark.asyncio +async def test_seed_parses_canned_prose(): + canned = json.dumps({ + "a_to_b_summary": "BotA and BotB went to college together.", + "a_to_b_knowledge_facts": ["BotB has a younger brother."], + "a_to_b_affinity_delta": 5, + "a_to_b_trust_delta": 3, + "b_to_a_summary": "BotB sees BotA as the responsible one.", + "b_to_a_knowledge_facts": ["BotA was once a TA."], + "b_to_a_affinity_delta": 4, + "b_to_a_trust_delta": 5, + }) + mock = MockLLMClient(canned=[canned]) + seed = await seed_inter_bot_edges( + mock, classifier_model="x", + bot_a_id="bot_a", bot_a_name="BotA", + bot_b_id="bot_b", bot_b_name="BotB", + relationship_prose="They went to college together; BotB still sees BotA as the responsible one.", + ) + assert "college" in seed.a_to_b_summary + assert seed.a_to_b_affinity_delta == 5 + + +@pytest.mark.asyncio +async def test_seed_empty_prose_returns_empty(): + mock = MockLLMClient(canned=[]) # never called + seed = await seed_inter_bot_edges( + mock, classifier_model="x", + bot_a_id="bot_a", bot_a_name="BotA", + bot_b_id="bot_b", bot_b_name="BotB", + relationship_prose="", + ) + assert seed == RelationshipSeed() +``` + +**Step 3: Minimal impl** + +Wraps `classify()` from `chat.llm.classify` with a `RelationshipSeed` schema and a system prompt explaining the task. + +**Step 5: Commit** + +```bash +git add chat/services/relationship_seed.py tests/test_relationship_seed.py +git commit -m "feat: relationship-seed service for first-co-appearance prompt" +``` + +--- + +## Wave 2 — Services + +After Wave 1 merges, dispatch Wave 2 in parallel. T39 and T40 are new files; T41 modifies `chat/services/memory_write.py` (additive — adds a new function alongside existing `record_turn_memory`). + +### Task 39: Interjection classifier service + +**Files:** +- Create: `chat/services/interjection.py` +- Create: `tests/test_interjection.py` + +**Spec:** Per requirements §6.2: when a guest is present and the addressee bot has just spoken, decide whether the *non-addressee* bot interjects. Classifier returns `{should_interject: bool, reason: str}`. Caller (T44 turn flow) generates the interjection beat as a brief follow-on response if `should_interject`. + +**Public API:** + +```python +class InterjectionDecision(BaseModel): + should_interject: bool = False + reason: str = "" + + +async def detect_interjection( + client: LLMClient, + *, + classifier_model: str, + addressee_name: str, + addressee_just_said: str, + silent_witness_name: str, + silent_witness_persona: str, + silent_witness_edge_to_addressee: dict, # {affinity, trust, summary} + silent_witness_edge_to_you: dict, + you_just_said: str, + timeout_s: float = 30.0, +) -> InterjectionDecision: + """Decide whether the silent witness bot interjects after the addressee + finishes speaking. Conservative bias — most turns should NOT interject + (return False). Trigger only when the witness's character would + plausibly speak up: jealousy, surprise, agreement worth voicing, + correcting a falsehood, etc. + """ +``` + +Classifier system prompt should explicitly bias toward `should_interject=false` (per spec: "addressee gets the floor"; interjection is the exception). + +**Tests:** 3 minimum. +1. Mock returns `{should_interject: true, reason: "..."}` → result is True. +2. Mock returns `{should_interject: false}` → result is False. +3. Classifier failure → fallback default (`should_interject=false`, `reason="fallback"`). + +**Commit:** `feat: interjection classifier service` + +--- + +### Task 40: Multi-entity state-update coordinator + +**Files:** +- Create: `chat/services/multi_state_update.py` +- Create: `tests/test_multi_state_update.py` + +**Spec:** Wraps the existing `chat.services.state_update.compute_state_update` (single-pair) into a coordinator that runs state updates for **all directed pairs of present entities**. With 3 entities (you, host, guest), that's 6 pairs: + +``` +you → host, host → you +you → guest, guest → you +host → guest, guest → host +``` + +Returns a list of `(source_id, target_id, StateUpdate)` tuples; caller (T44) emits one `edge_update` event per tuple via `append_and_apply`. + +**Public API:** + +```python +async def compute_state_updates_for_present( + client: LLMClient, + *, + classifier_model: str, + present_ids: list[str], # e.g. ["you", "bot_a", "bot_b"] + present_names: dict[str, str], # id -> display name + personas: dict[str, str], # id -> persona blob + prior_edges: dict[tuple[str, str], dict], # (src, tgt) -> {affinity, trust, summary} + recent_dialogue: list[dict], # [{speaker, text}, ...] + timeout_s: float = 30.0, +) -> list[tuple[str, str, StateUpdate]]: + """Run compute_state_update for every directed pair where source != target. + Returns list of (source_id, target_id, update) tuples. Skips pairs + involving "you" with itself. + """ +``` + +Implementation: nested loops over `present_ids`, sequential calls to `compute_state_update` (parallel calls would exceed the Featherless 2-connection cap from the FeatherlessClient semaphore). + +**Tests:** 3 minimum. +1. With 2 present (you, host) → returns 2 updates (existing 1A/2D parity). +2. With 3 present (you, host, guest) → returns 6 updates, one per directed non-self pair. +3. Failures in one pair don't kill the whole batch (per-pair `compute_state_update` already has a default fallback). + +**Commit:** `feat: multi-entity state-update coordinator` + +--- + +### Task 41: Multi-witness memory write helper + +**Files:** +- Modify: `chat/services/memory_write.py` (add `record_turn_memory_for_present` alongside existing `record_turn_memory`; do NOT remove or change `record_turn_memory`) +- Add tests to: `tests/test_memory_write.py` + +**Spec:** Currently Phase 1's `record_turn_memory(conn, *, chat_id, host_bot_id, narrative_text, ...)` writes a single memory event for the host bot's POV. With a guest present, we need: +- One memory in the host's store (witness mask `[1, 1, 1]` if you/host/guest present) +- One memory in the guest's store (same witness mask, owner = guest_bot_id) + +"You" still doesn't have a memory store in v1 (per §5.4 / §11.2). + +**New helper:** + +```python +def record_turn_memory_for_present( + conn, + *, + chat_id: str, + host_bot_id: str, + guest_bot_id: str | None, + narrative_text: str, + scene_id: int | None = None, + chat_clock_at: str | None = None, + source: str = "direct", + significance: int = 1, +) -> dict[str, tuple[int, int]]: + """Write a memory_written event for each present bot witness (host + always; guest if guest_bot_id is not None). Returns {bot_id: + (event_id, memory_id)}. + + Witness mask is [1, 1, 1] when guest is present, [1, 1, 0] otherwise + (mirrors Phase 1 single-bot behavior when guest_bot_id is None). + """ +``` + +Implementation: appends one `memory_written` event per present bot, calling `append_and_apply` for each, and queries the resulting `memories.id` per owner+chat just like Phase 1's `record_turn_memory`. + +**Tests:** 3 minimum, added to `tests/test_memory_write.py`: +1. With `guest_bot_id=None`, behaves identically to `record_turn_memory` (one memory for host, witness `[1, 1, 0]`). +2. With `guest_bot_id="bot_b"`, writes two memories — one each for host and guest, both with witness `[1, 1, 1]`. +3. Returned dict keys match `{host_bot_id, guest_bot_id}` (or just `{host_bot_id}` when no guest). + +**Commit:** `feat: multi-witness memory write helper` + +--- + +## Wave 3 — Drawer guest support (single task) + +This wave is one task because all Phase 2 drawer work touches the same two files (`chat/web/drawer.py` and `chat/templates/_drawer.html`). Splitting would force serial execution with conflict resolution. Single-task wave runs alone. + +### Task 42: Drawer guest support (add/remove + render) + +**Files:** +- Modify: `chat/web/drawer.py` (add `POST /chats/{chat_id}/drawer/guest/add`, `POST /chats/{chat_id}/drawer/guest/remove`; extend `drawer` GET handler to query guest state when present) +- Modify: `chat/templates/_drawer.html` (render guest activity, guest edges, group node summary; add "Add guest" form and "Remove guest" button when applicable) +- Create: `tests/test_drawer_guest.py` + +**Spec:** + +**GET /chats/{chat_id}/drawer** (extend, don't replace): +- Read `chat["guest_bot_id"]` from the existing `get_chat` query. +- If guest present: also fetch `get_bot(conn, guest_bot_id)`, `get_activity(conn, guest_bot_id)`, edges in both `host ↔ guest` directions, edges in both `you ↔ guest` directions, and `get_group_node(conn, chat_id)`. +- Pass all of this to the template. + +**Template changes:** +- New section "Guest" rendering guest's name, activity, and the four edges involving the guest. +- New section "Group" rendering `group_node.summary` and `group_node.dynamic` when present. +- "Add guest" button → expands form with: bot selector (dropdown of authored bots not currently in this chat) + relationship prose textarea (the "have they met?" prompt). +- "Remove guest" button visible when a guest is present. + +**POST /chats/{chat_id}/drawer/guest/add** route: +1. Read form: `guest_bot_id`, `relationship_prose`. +2. 404 if chat or guest_bot is missing. +3. 400 if guest_bot_id == host_bot_id. +4. 400 if a guest is already present. +5. Call `seed_inter_bot_edges` (T38) with the prose. May produce empty seed if prose is blank. +6. Append events: `guest_added`, then up to 2 `edge_update` events (host ↔ guest deltas from the seed). Use `append_and_apply` for each. +7. If all 3 entities are now present and no `group_node` row exists for this chat, append `group_node_initialized` with members=[you, host, guest] and empty summary/dynamic. +8. Return refreshed drawer partial. + +**POST /chats/{chat_id}/drawer/guest/remove** route: +1. 404 if chat missing; 400 if no guest present. +2. Append `scene_closed` for the active scene (per §7.5: removing the guest closes the current scene). +3. Append `guest_removed`. +4. (Per §7.5 the host's chat then implicitly opens a new scene with you+host. For Phase 2, leave that as a manual "next user message creates the new scene" — same as Phase 1 mid-chat reset semantics. Phase 3 may auto-open.) +5. Return refreshed drawer partial. + +**Tests (`tests/test_drawer_guest.py`):** 6 minimum. +1. GET drawer with no guest → no "Guest" section in body. +2. POST add guest → 303-or-200 with refreshed drawer; chat.guest_bot_id is set; `group_node` row created; relationship-seed mock returns canned values; edges have the seeded values. +3. POST add guest with empty relationship_prose → guest added; `seed_inter_bot_edges` short-circuits; edges remain at default 50/50. +4. POST add guest when one is already present → 400. +5. POST remove guest → guest_bot_id NULL, scene_closed event written. +6. GET drawer with guest present → "Guest" section + group_node summary visible. + +**Commit:** `feat: drawer guest add/remove + render` + +**Notes for implementer:** +- The guest-bot-selector dropdown lists bots from `list_bots(conn)` minus the host. Don't filter for "bots not in any chat" — guests can be in multiple chats simultaneously (each chat has its own scene state). +- The "have they met?" prose textarea is the per-pair prompt. v1 only fires it on first co-appearance globally; for v2, fire it every time a `(host, guest)` pair has no existing `host → guest` edge. After the first add, the edge exists, so subsequent adds skip the prose (or render it disabled with "you've already met"). Treat this as Phase 2.5 polish if it gets fiddly — for T42 just always show the prose textarea, blank by default. +- The drawer route already uses `Depends(get_conn)` and templates; reuse the existing dependency and TEMPLATES instance. + +--- + +## Wave 4a — Multi-entity prompt + scene close (parallel) + +T43 and T45 touch different files (`prompt.py` and `scene_summarize.py`). Dispatch both in parallel. + +### Task 43: Multi-entity prompt assembly + +**Files:** +- Modify: `chat/services/prompt.py` (extend `assemble_narrative_prompt` to handle a `guest_id` parameter and fetch guest activity, guest edge, group node into the prompt blocks) +- Add tests to: `tests/test_prompt.py` + +**Spec:** The current `assemble_narrative_prompt(conn, *, chat_id, speaker_bot_id, addressee="you", ...)` only handles you+host. Extend: + +- Accept a `guest_id: str | None = None` parameter (auto-fetched from `chat.guest_bot_id` if not passed; explicit override for tests). +- When `guest_id` is provided: + - Activity block includes the guest's activity (`get_activity(conn, guest_id)`). + - If `speaker_bot_id == guest_id`, the addressee defaults to "you" but caller can override. + - "Speaker's other edges" SHOULD-tier block includes speaker → non-addressee (e.g., host → guest if speaker is host and addressee is you). + - MUST-tier identity block unchanged (still just speaker). + - Group-node summary becomes a SHOULD-tier block when all three are present (after MUST, before retrieved memories). +- Token budget tier ordering unchanged. + +**Tests:** 4 minimum, added to `tests/test_prompt.py`: +1. With `guest_id=None`, output matches existing 2-entity behavior (regression). +2. With `guest_id="bot_b"` present and group_node populated, the assembled system message contains: speaker identity, guest activity, group_node summary, host→guest edge for the speaker. +3. Speaker is the guest (`speaker_bot_id == guest_id`), addressee="you" → guest's edges and group node correctly oriented. +4. Tight budget forces NICE-trim of guest activity → MUST blocks (speaker identity, edge_to_addressee, last 4 turns) survive. + +**Commit:** `feat: multi-entity prompt assembly with guest activity, edges, group node` + +--- + +### Task 45: Multi-entity per-POV summaries on scene close + +**Files:** +- Modify: `chat/services/scene_summarize.py` (extend `apply_scene_close_summary` to write per-POV summaries for **each present witness** with a memory store, not just host) +- Modify: tests in `tests/test_per_pov_summary.py` + +**Spec:** Phase 1's `apply_scene_close_summary` only summarizes from the host bot's POV. For Phase 2: + +- Determine present witnesses with memory stores: host always; guest if `chat.guest_bot_id is not None`. +- For each, generate an independent per-POV summary via `summarize_scene` (the existing classifier wrapper). Each call uses **that bot's** persona, `you_name`, prior `bot → you` edge summary, and the same dialogue. +- Update each owner's memories of the closing scene with their per-POV summary. +- Update **all directed bot → you edges** with per-POV-derived `summary` content. +- If `group_node` exists for this chat, also append `group_node_updated` event with new `summary` and `dynamic` derived from the group view (run `summarize_scene` once with `bot_name="group"`, `bot_persona="all participants"` for a meta-summary). For v1 simplicity, the meta-summary can be naive concat of the host's per-POV summary + guest's per-POV summary; full LLM-merged group view is deferred to Phase 2.5. + +**Tests:** 4 minimum, added to `tests/test_per_pov_summary.py`: +1. With no guest, behavior matches Phase 1 (regression test). +2. With guest, `apply_scene_close_summary` calls `summarize_scene` twice (one per bot witness) — assert mock called 2x. +3. After close, each bot's memories of the closed scene have their respective per-POV summary (different text). +4. With group_node present, after close `get_group_node(conn, chat_id).summary` is updated. + +**Commit:** `feat: per-POV summaries on close for each present witness` + +--- + +## Wave 4b — Turn flow integration (single task; depends on 4a) + +T44 ties everything together. It modifies `chat/web/turns.py` (post_turn) and `chat/services/regenerate.py` to use the new multi-entity primitives. Must run after Wave 4a is merged so `assemble_narrative_prompt` accepts `guest_id` and `apply_scene_close_summary` handles guest. + +### Task 44: Multi-entity turn flow + +**Files:** +- Modify: `chat/web/turns.py` (rewrite `post_turn` to: parse turn → optionally close scene → assemble prompt with guest → narrative stream → write memories for ALL witnesses → state updates for ALL pairs → interjection check + interjection narrative if needed) +- Modify: `chat/services/regenerate.py` (mirror the changes — regenerated turn rebuilds with guest in scope) +- Modify: tests in `tests/test_turn_flow.py` (add multi-entity scenarios) + +**Spec:** Refactored `post_turn` flow: + +``` +1. Validate prose (existing 400 check). +2. Look up chat, host_bot, guest_bot (None if no guest). +3. Parse turn (existing parse_turn). +4. Append user_turn event. +5. Append assistant_turn_started. +6. Detect scene close (existing path; runs even with guest). +7. (Recent dialogue read with multi-witness in mind — same query.) +8. Determine ADDRESSEE: simplest v2 heuristic — addressee is host unless + prose explicitly names guest_bot.name. Pass to assemble_narrative_prompt. +9. Assemble narrative prompt with speaker=addressee, guest_id passed. +10. Stream narrative; broadcast tokens; commit assistant_turn (existing). +11. Write memories: record_turn_memory_for_present(host, guest). +12. State updates: compute_state_updates_for_present, then append_and_apply + one edge_update per pair. +13. INTERJECTION CHECK (only if guest present and addressee != silent witness): + a. Call detect_interjection with the silent witness as candidate. + b. If should_interject: assemble narrative prompt with speaker=silent_witness, + addressee=host (or whoever just spoke), and instruct briefly. + c. Stream second narrative; broadcast as second turn_html; commit second + assistant_turn event. + d. Run state updates + memory writes for the interjection turn too + (smaller scope — just the interjector's outgoing edges + memories). +14. Scene close summary (existing path; now multi-witness via T45). +15. Broadcast turn_html for primary + interjection (if any). +16. Return 204. +``` + +**Addressee heuristic (Phase 2 v1):** simple substring match on bot names. If both names appear or neither: addressee defaults to host. Phase 2.5 / Phase 3 may improve with a classifier call. + +**Cancel & truncated:** unchanged from Phase 1 — both halves of a streaming turn (primary + interjection) cancel together. + +**`regenerate.py` changes:** parallel to `turns.py` — multi-entity prompt assembly + multi-witness memory + multi-pair state update. Interjection regeneration is deferred to Phase 2.5 (regenerate only the addressee's turn for v2). + +**Tests added to `tests/test_turn_flow.py`:** 5 minimum. +1. Single-bot turn (no guest): full suite still passes (regression). +2. Multi-bot turn, no interjection: `post_turn` produces 1 user_turn + 1 assistant_turn + 6 edge_updates + 2 memory_written events. Mock interjection returns `should_interject=false`. +3. Multi-bot turn, with interjection: produces user_turn + 2 assistant_turns + 12 edge_updates + 4 memory_written events. +4. Multi-bot turn, scene close fires: `scene_closed` + multi-POV summaries written (per T45). +5. Addressee detection: prose `"BotB, what do you think?"` routes to BotB as speaker. + +**Commit:** `feat: multi-entity turn flow with interjection support` + +**Notes for implementer:** +- This task is the largest in Phase 2 by line count. Budget for ~150-300 lines of changes across `turns.py` and tests. The implementer should split commits if it helps clarity (one commit for primary turn, one for interjection, one for tests). +- Update the existing `_seed_chat` helper in `tests/test_turn_flow.py` to optionally seed a guest, and add `_seed_chat_with_guest` if cleaner. +- The fixture for the LLM mock now needs to provide canned responses for: parse_turn + scene_close_detect + narrative + state_updates×6 + interjection_decision + (optionally) interjection_narrative + state_updates×2 (interjection's outgoing only). + +--- + +## Wave 5 — Polish (parallel) + +Three independent tasks. Dispatch all three in parallel after Wave 4b merges. + +### Task 46: Witness filter test coverage + +**Files:** +- Create: `tests/test_witness_filter_multi.py` + +**Spec:** Phase 1 tested witness filtering with single-bot scenarios. Phase 2 needs explicit tests for the cross-witness cases: +- Memory with witness `[1, 1, 0]`: visible to host, not guest (when guest queries from their POV). +- Memory with witness `[0, 1, 1]`: visible to host and guest, not "you". +- Secondhand-source memories: `source: "told_by:bot_a"`, witness flag for bot_b set, reliability < 1.0. + +5 tests minimum. + +**Commit:** `test: witness filter coverage for multi-entity scenarios` + +--- + +### Task 47: Bot reset cascades to guest scenes + +**Files:** +- Modify: `chat/state/entities.py` (`_apply_bot_reset` extended to also remove the bot's `guest_bot_id` references in OTHER chats: `UPDATE chats SET guest_bot_id = NULL WHERE guest_bot_id = ?`; remove the bot's activity row in those chats too) +- Modify: tests in `tests/test_reset.py` (add scenario: bot is guest in another's chat; reset clears the guest reference) + +**Spec:** Currently `bot_reset` purges the bot's own chat state, memories, and edges. With Phase 2, a bot can be a guest in another bot's chat — that reference must also clear. Otherwise the host's chat sees a stale guest_bot_id pointing at a phantom bot. + +Update `_apply_bot_reset` handler: + +```python +# After existing purges: +conn.execute("UPDATE chats SET guest_bot_id = NULL WHERE guest_bot_id = ?", (bot_id,)) +conn.execute("DELETE FROM activity WHERE entity_id = ?", (bot_id,)) # already there; covers all chats +``` + +(Activity is keyed by entity_id, so the existing line handles cross-chat activity rows already.) + +**Tests:** 2 minimum, added to `tests/test_reset.py`. +1. BotB is guest in BotA's chat. Reset BotB. Assert `chat_bot_a.guest_bot_id` is NULL. +2. BotB has memories (witness flag set, owner=bot_b) from being guest in BotA's chat. Reset BotB. Assert those memories are gone. + +**Commit:** `fix: bot_reset cascades to guest references in other chats` + +--- + +### Task 48: Phase 2 documentation update + +**Files:** +- Modify: `CLAUDE.md` (add "Phase 2 status" section; update "Behavioral defaults" with multi-entity additions; add to "Phase 1.5 / 2 cleanup backlog" any v2 follow-ups discovered during execution) +- Modify: `docs/plans/2026-04-26-v1-requirements-design.md` (mark Phase 2 deliverables as "shipped" in the appendix decisions log) + +**Spec:** Documentation-only task. Run last in Phase 2 so it captures any deviations from the plan that emerged during execution. Reflect: +- Multi-entity scene support (you + host + guest). +- Interjection model (default false; explicit signals only). +- Per-POV summaries on close for all witnesses with memory stores. +- Group node populated on first 3-entity scene; updated on close. +- Phase 2 known limitations: + - "Meanwhile…" (scene config 4 — bot+bot without you) deferred to Phase 3. + - Interjection regeneration deferred (regenerate only acts on the addressee turn). + - Addressee detection is a simple name-match heuristic (no classifier call yet). + +**Commit:** `docs: phase 2 status, behavioral defaults, deferred items` + +--- + +## Wrap-up + +After Wave 5 lands: + +1. **Run full suite** on `phase-2`: should be ~210+ tests passing (168 from Phase 1 + ~45 new). +2. **Manual smoke**: + - Add a guest to one of the seeded bots' chats via the drawer. + - Verify "have they met?" prose seeds inter-bot edges. + - Play a few turns; verify host responds normally; verify guest occasionally interjects. + - Close the scene; check drawer for two distinct per-POV summaries. + - Remove guest mid-scene; check scene_closed fires. + - Reset a guest bot from another chat; verify guest_bot_id reference clears. +3. **Push `phase-2`** to gitea. +4. **Open PR** `phase-2 → main`. +5. **Phase 2.5 backlog candidates** (track in CLAUDE.md): interjection regenerate UI, classifier-based addressee detection, group-node LLM-merged meta-summary, drawer "first-meeting" gate vs "they already know each other" toggle, witness flag editing in drawer (currently read-only by spec). + +--- + +## Notes for the controller running this plan + +- **Don't dispatch Wave 4b until Wave 4a is merged AND tested green on `phase-2`.** Wave 4b's `turns.py` changes import the new `assemble_narrative_prompt` signature from Wave 4a's `prompt.py`; missing that produces import-time failures. +- **After each parallel wave**, the controller should run a code-review subagent (`subagent-driven-development` skill's two-stage review pattern) on each task before merging to `phase-2`. For purely mechanical tasks, a combined spec+quality review is acceptable. +- **If a parallel wave's merge produces a conflict**, the wave's file-disjointness assumption was violated. Bisect the affected pair, fix the offending task in a follow-up commit on `phase-2`, and proceed. +- **Token-spend rough estimate**: Phase 2 should be ~30-40% the size of Phase 1 (smaller scope; reuses Phase 1 patterns). Per-task token spend similar to Phase 1. +- **DO NOT modify Phase 1 code paths** unless explicitly required (e.g., Wave 5 T47 modifies `_apply_bot_reset` because the cascade is genuinely new behavior). The single-bot path must continue to work end-to-end after each wave. diff --git a/docs/plans/2026-04-26-v2-phase2-implementation.md.tasks.json b/docs/plans/2026-04-26-v2-phase2-implementation.md.tasks.json new file mode 100644 index 0000000..56d2934 --- /dev/null +++ b/docs/plans/2026-04-26-v2-phase2-implementation.md.tasks.json @@ -0,0 +1,20 @@ +{ + "planPath": "docs/plans/2026-04-26-v2-phase2-implementation.md", + "tasks": [ + {"id": 36, "subject": "T36: group_node schema + projector handlers", "status": "pending", "wave": 1, "parallelGroup": "wave-1"}, + {"id": 37, "subject": "T37: guest_added / guest_removed event handlers", "status": "pending", "wave": 1, "parallelGroup": "wave-1"}, + {"id": 38, "subject": "T38: relationship-seed service for first-co-appearance prompt", "status": "pending", "wave": 1, "parallelGroup": "wave-1"}, + {"id": 39, "subject": "T39: interjection classifier service", "status": "pending", "wave": 2, "parallelGroup": "wave-2", "blockedBy": [37]}, + {"id": 40, "subject": "T40: multi-entity state-update coordinator", "status": "pending", "wave": 2, "parallelGroup": "wave-2", "blockedBy": [37]}, + {"id": 41, "subject": "T41: multi-witness memory write helper", "status": "pending", "wave": 2, "parallelGroup": "wave-2", "blockedBy": [37]}, + {"id": 42, "subject": "T42: drawer guest add/remove + render", "status": "pending", "wave": 3, "parallelGroup": null, "blockedBy": [36, 37, 38]}, + {"id": 43, "subject": "T43: multi-entity prompt assembly with guest activity, edges, group node", "status": "pending", "wave": 4, "parallelGroup": "wave-4a", "blockedBy": [36, 37]}, + {"id": 45, "subject": "T45: per-POV summaries on close for each present witness", "status": "pending", "wave": 4, "parallelGroup": "wave-4a", "blockedBy": [36, 37]}, + {"id": 44, "subject": "T44: multi-entity turn flow with interjection support", "status": "pending", "wave": 4, "parallelGroup": null, "blockedBy": [39, 40, 41, 43, 45]}, + {"id": 46, "subject": "T46: witness filter test coverage for multi-entity scenarios", "status": "pending", "wave": 5, "parallelGroup": "wave-5", "blockedBy": [44]}, + {"id": 47, "subject": "T47: bot_reset cascades to guest references in other chats", "status": "pending", "wave": 5, "parallelGroup": "wave-5", "blockedBy": [37]}, + {"id": 48, "subject": "T48: Phase 2 documentation update", "status": "pending", "wave": 5, "parallelGroup": "wave-5", "blockedBy": [44]} + ], + "lastUpdated": "2026-04-26T00:00:00Z", + "notes": "13 tasks across 6 waves (1, 2, 3, 4a, 4b, 5). Waves 1, 2, 4a, 5 are parallel-safe (file-disjoint within each). Waves 3 and 4b are single-task. Use Agent tool with isolation: 'worktree' to dispatch parallel tasks. Merge each wave's worktrees back into phase-2 before dispatching the next wave. See plan §Parallel-Execution Strategy for full guidance." +} diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..de06982 --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,31 @@ +[project] +name = "chat" +version = "0.1.0" +requires-python = ">=3.11" +dependencies = [ + "fastapi>=0.110", + "uvicorn[standard]>=0.30", + "httpx>=0.27", + "pydantic>=2.6", + "pydantic-settings>=2.2", + "openai>=1.30", + "instructor>=1.3", + "tiktoken>=0.7", + "jinja2>=3.1", + "aiosqlite>=0.20", + "python-multipart>=0.0.9", +] + +[project.optional-dependencies] +dev = ["pytest>=8", "pytest-asyncio>=0.23", "freezegun>=1.4"] + +[build-system] +requires = ["setuptools>=61"] +build-backend = "setuptools.build_meta" + +[tool.setuptools.packages.find] +include = ["chat*"] + +[tool.pytest.ini_options] +pythonpath = ["."] +asyncio_mode = "auto" diff --git a/scripts/seed_sample_bots.py b/scripts/seed_sample_bots.py new file mode 100644 index 0000000..583cd09 --- /dev/null +++ b/scripts/seed_sample_bots.py @@ -0,0 +1,253 @@ +"""Seed three sample bots via direct event-log append. + +Idempotent: re-running skips bots whose ids already exist. + +Run from the repo root: + .venv/bin/python scripts/seed_sample_bots.py + +After running, walk each bot through kickoff parse-and-confirm at: + http://127.0.0.1:8000/bots//kickoff +""" + +from __future__ import annotations + +from chat.config import load_settings +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations +from chat.eventlog.log import append_and_apply +from chat.state.entities import get_bot + +# Trigger handler registration. +import chat.state.entities # noqa: F401 +import chat.state.edges # noqa: F401 +import chat.state.memory # noqa: F401 +import chat.state.world # noqa: F401 +import chat.state.manual_edit # noqa: F401 + + +SAMPLES: list[dict] = [ + { + "id": "maya", + "name": "Maya Chen", + "persona": ( + "31, senior product designer at the same company you work for. " + "Sharp eye for what isn't said. Outwardly composed and dryly funny; " + "privately prone to overthinking and drafting texts she never sends. " + "Came out of a five-year relationship six months ago and is still " + "pretending she's fine." + ), + "voice_samples": [ + ( + "\"You look like someone who needs water more than another coffee. " + "I'm just saying.\"" + ), + ( + "She tilts her laptop screen toward you without looking up. " + "\"Tell me which one. Don't think about it. The first one your eye " + "lands on is the right one.\"" + ), + ( + "A pause. \"I'm going to head out. ...Unless you want company on the " + "elevator. Which is a weird sentence I just said out loud.\"" + ), + ], + "traits": [ + "dry humor", + "observant", + "perfectionist", + "quick to deflect compliments", + "late-night texter", + "runs on cold brew", + "slow to trust", + "draws in margins when bored", + "hates small talk", + "secretly sentimental", + ], + "backstory": ( + "Grew up in Vancouver, only child of immigrant parents. Design school " + "in Toronto. Three years at this company; took the senior role eight " + "months ago after the previous lead left abruptly. Her father died of " + "a stroke last fall — she flew home for the funeral and was back at " + "her desk on Monday. She has not really talked to anyone about it, " + "including her mother, including her therapist, including her best " + "friend. She works too much. She knows she works too much." + ), + "initial_relationship_to_you": ( + "Coworkers for about eighteen months. Two desks over. You've been on " + "the same product team for the last year. She thinks you're one of the " + "very few people at the company who actually thinks before speaking, " + "which she finds annoying and also relieving. The two of you have " + "lunch sometimes. You stayed late together once before the big launch " + "and she doesn't remember exactly what was said but she remembers the " + "feeling of the empty office. She has not admitted anything to " + "herself. You probably haven't either." + ), + "kickoff_prose": ( + "It's 9:14 on a Thursday and you and Maya are the only people left on " + "the floor. The deck is due in the morning. She has her shoes off " + "under her desk. The kitchen lights flicker once and then steady. She " + "slides her chair back and rubs her eyes with the heels of her hands. " + "\"Okay,\" she says, to no one in particular, \"tell me honestly. " + "Slide eleven — does that read as ambitious or as desperate.\"" + ), + }, + { + "id": "eli", + "name": "Eli Park", + "persona": ( + "34, freelance illustrator. Quiet, tactile, generous with attention " + "but stingy with words. Bakes when stressed. Falls asleep on the " + "couch with his glasses on. Loves you in the kind of way that doesn't " + "need to be announced." + ), + "voice_samples": [ + ( + "\"Hey.\" A pause, like he's deciding if it's worth saying. \"You " + "ate, right?\"" + ), + ( + "He kisses the top of your head and keeps walking, not breaking " + "stride. \"Don't fall asleep on the bathroom floor again. That's " + "all I'm saying.\"" + ), + ( + "\"You don't have to. I just.\" He looks at his hands. \"I just " + "like it when you're around when I'm working. It's stupid. It's " + "whatever.\"" + ), + ], + "traits": [ + "warm", + "present", + "distractible", + "terrible at confrontation", + "leaves coffee mugs in every room", + "draws on napkins", + "gets up at 6am to paint", + "owns far too many sweaters", + "never throws anything away", + "holds your hand without thinking about it", + ], + "backstory": ( + "Born and raised in Queens to Korean parents who ran a dry cleaner. " + "Older sister Lena died in a car accident when he was nineteen — the " + "year he left for art school. He won't talk about her on most days " + "but he keeps a small photo of her in his wallet, and on her birthday " + "he stops talking by 7pm and goes to bed early. He has been a " + "freelance illustrator for nine years. His work has appeared in The " + "New Yorker twice and he refuses to make this a personality trait. " + "He pays his bills on time. He loses his keys constantly." + ), + "initial_relationship_to_you": ( + "You've been together for four years, living together for two. He " + "proposed last summer, kind of — it was tentative and circular and " + "the question wasn't really a question, and you both laughed and " + "didn't really resolve it, and somewhere there is an unspent ring in " + "a sock drawer. You bicker about laundry and the right way to load a " + "dishwasher. He has seen you cry over genuinely stupid commercials. " + "You are each other's first call. You sleep on the left side." + ), + "kickoff_prose": ( + "Sunday morning, late. The blinds are still down. Eli is propped " + "against the headboard reading something on his phone, his glasses " + "pushed up into his hair. You've been awake for a while; he just " + "noticed. He sets the phone face-down on his chest and looks over at " + "you with the small private smile he only uses in this room. \"Hi,\" " + "he says, like it's a whole sentence." + ), + }, + { + "id": "sam", + "name": "Samira Reyes", + "persona": ( + "28, bartender at a small cocktail bar near where you live, doing a " + "part-time master's in psychology she refuses to talk about. " + "Confident posture, careful words. Reads people fast and shares the " + "readings only when she likes them. Single by deliberate choice for " + "the last two years." + ), + "voice_samples": [ + ( + "\"You're back.\" She says it without looking up from polishing " + "the glass. \"Same as last time, or are we trying something new " + "tonight.\"" + ), + ( + "A long look. \"I'm going to ask you a question and you're not " + "going to answer it carefully. The first thing that comes into " + "your head. Ready.\"" + ), + ( + "\"Don't tip me extra because we talked. I'm being serious. " + "That's a different transaction and I don't want it confused.\"" + ), + ], + "traits": [ + "observant", + "blunt", + "kind in unexpected ways", + "reads tarot for fun (doesn't believe in it)", + "drinks black coffee", + "runs at 5am", + "doesn't suffer fools", + "never forgets a face", + "occasional smoker when something is bothering her", + "owns three identical black t-shirts", + ], + "backstory": ( + "Born and raised in El Paso to a single mother who waitressed nights. " + "Came north five years ago for undergrad on a scholarship. Funded the " + "master's herself by bartending — she's careful about money in a way " + "that took being broke to learn. Her undergraduate thesis was on " + "attachment styles and she will not tell you what her own attachment " + "style is. Her mother passed away two years ago after a long illness, " + "and she went home for a month and came back different in ways she " + "can't articulate." + ), + "initial_relationship_to_you": ( + "You've talked at her bar maybe six times over the last month. She " + "knows your drink. The conversations have started lasting longer than " + "they should — you stay until close more often than you mean to. Last " + "week you walked her to her car at 1am because the lot is dim. " + "Nothing happened. You just talked, leaning on the hood of her old " + "Civic, longer than either of you intended. Neither of you has texted " + "the other since. Neither of you has stopped thinking about it." + ), + "kickoff_prose": ( + "It's 11:47 on a Tuesday — slow night. There's exactly one other " + "customer at the far end of the bar, finishing a beer he stopped " + "drinking ten minutes ago. Sam is wiping down the counter in long " + "unhurried passes. She glances up when the door chimes and the small " + "surprise on her face is gone before you'd swear it was there. " + "\"Look who it is,\" she says, even and unreadable, and pulls down a " + "glass without asking what you want." + ), + }, +] + + +def main() -> None: + settings = load_settings() + apply_migrations(settings.db_path) + + created: list[str] = [] + skipped: list[str] = [] + + with open_db(settings.db_path) as conn: + for spec in SAMPLES: + if get_bot(conn, spec["id"]) is not None: + skipped.append(spec["id"]) + continue + append_and_apply(conn, kind="bot_authored", payload=spec) + created.append(spec["id"]) + + print(f"created: {created}") + print(f"skipped (already existed): {skipped}") + print() + print("Walk each new bot through kickoff parse-and-confirm:") + for bot_id in created: + print(f" http://127.0.0.1:8000/bots/{bot_id}/kickoff") + + +if __name__ == "__main__": + main() diff --git a/tests/__init__.py b/tests/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/tests/test_backup.py b/tests/test_backup.py new file mode 100644 index 0000000..1fcfd29 --- /dev/null +++ b/tests/test_backup.py @@ -0,0 +1,92 @@ +"""Tests for nightly DB backups (T32). + +The backup service is intentionally simple: a flat ``data/backups/`` dir +containing timestamped copies of ``chat.db``, with retention of the most +recent 14. The scheduling decision (``should_take_backup``) is a pure +function of clock + filesystem state so it can be unit-tested without +spinning up the BackgroundWorker tick loop. +""" + +from __future__ import annotations + +from datetime import datetime +from unittest.mock import patch + +from chat.services.backup import ( + prune_backups, + should_take_backup, + take_backup, +) + + +def test_take_backup_creates_timestamped_copy(tmp_path): + db = tmp_path / "chat.db" + db.write_text("fake db contents") + backup_path = take_backup(db_path=db, data_dir=tmp_path / "data") + assert backup_path.exists() + assert backup_path.name.startswith("chat-") + assert backup_path.name.endswith(".db") + # Contents copied + assert backup_path.read_text() == "fake db contents" + # Located in data/backups/ + assert backup_path.parent == tmp_path / "data" / "backups" + + +def test_prune_keeps_last_14(tmp_path): + backup_dir = tmp_path / "data" / "backups" + backup_dir.mkdir(parents=True) + # Create 17 dummy backup files spanning days 1..17 of Jan 2026. + # Filenames sort lexicographically by the embedded timestamp, so + # prune_backups should drop the three oldest. + for i in range(1, 18): + (backup_dir / f"chat-202601{i:02d}T000000Z.db").write_text( + f"backup {i}" + ) + removed = prune_backups(tmp_path / "data", keep=14) + assert removed == 3 + remaining = sorted(backup_dir.glob("chat-*.db")) + assert len(remaining) == 14 + # Days 1, 2, 3 removed; day 4 is now the oldest retained backup. + assert remaining[0].name == "chat-20260104T000000Z.db" + + +def test_should_take_backup_when_no_prior_and_target_hour_matches(tmp_path): + from chat.services import backup as backup_mod + + class FakeDateTime(datetime): + @classmethod + def now(cls, tz=None): + return datetime(2026, 4, 26, 3, 0, 0) + + with patch.object(backup_mod, "datetime", FakeDateTime): + assert should_take_backup(tmp_path / "data") is True + + +def test_should_not_take_backup_outside_target_hour(tmp_path): + from chat.services import backup as backup_mod + + class FakeDateTime(datetime): + @classmethod + def now(cls, tz=None): + return datetime(2026, 4, 26, 14, 0, 0) + + with patch.object(backup_mod, "datetime", FakeDateTime): + assert should_take_backup(tmp_path / "data") is False + + +def test_should_not_take_backup_when_recent_backup_exists(tmp_path): + backup_dir = tmp_path / "data" / "backups" + backup_dir.mkdir(parents=True) + recent = backup_dir / "chat-recent.db" + recent.write_text("x") + # mtime defaults to "now" — within the 23h freshness window so + # should_take_backup must return False even at the target hour. + from chat.services import backup as backup_mod + + class FakeDateTime(datetime): + @classmethod + def now(cls, tz=None): + return datetime(2026, 4, 26, 3, 0, 0) + + with patch.object(backup_mod, "datetime", FakeDateTime): + assert should_take_backup(tmp_path / "data") is False diff --git a/tests/test_bot_authoring.py b/tests/test_bot_authoring.py new file mode 100644 index 0000000..5b8a82d --- /dev/null +++ b/tests/test_bot_authoring.py @@ -0,0 +1,132 @@ +from __future__ import annotations + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app + + +@pytest.fixture +def client(tmp_path, monkeypatch): + config_path = tmp_path / "config.toml" + config_path.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(config_path)) + monkeypatch.setenv("CHAT_DB_PATH", str(tmp_path / "test.db")) + with TestClient(app) as c: + yield c + + +def test_get_new_bot_form_renders(client): + response = client.get("/bots/new") + assert response.status_code == 200 + body = response.text.lower() + assert " None: + """Author a ``you_entity`` so the first-run middleware doesn't redirect.""" + from chat.db.connection import open_db + + with open_db(db_path) as conn: + append_event( + conn, + kind="you_authored", + payload={"name": "Me", "pronouns": "", "persona": ""}, + ) + project(conn) + + +def _author_bot_and_chat(db_path: Path, bot_id: str = "bot_a") -> None: + """Insert a you_entity, bot, and chat via the event log (skip kickoff route).""" + from chat.db.connection import open_db + + with open_db(db_path) as conn: + append_event( + conn, + kind="you_authored", + payload={"name": "Me", "pronouns": "", "persona": ""}, + ) + append_event( + conn, + kind="bot_authored", + payload={ + "id": bot_id, + "name": "BotA", + "persona": "thoughtful, observant", + "voice_samples": [], + "traits": ["shy"], + "backstory": "", + "initial_relationship_to_you": "coworker", + "kickoff_prose": "you stay late at the office; she's there too", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": f"chat_{bot_id}", + "host_bot_id": bot_id, + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + project(conn) + + +def test_root_redirects_to_chats_when_setup_complete(client, tmp_path): + # With both you_entity and a bot present, the first-run middleware + # passes through and the nav router sends "/" → "/chats". + _author_bot_and_chat(tmp_path / "test.db", "bot_a") + response = client.get("/", follow_redirects=False) + assert response.status_code == 303 + assert response.headers["location"] == "/chats" + + +def test_chats_list_empty_state(client, tmp_path): + # Author you + a bot but NO chats — should render the empty-state + # chats list, not redirect. + _author_bot_and_chat(tmp_path / "test.db", "bot_a") + # Drop the chat row so we hit the empty-state branch (the helper + # creates a chat — undo it via a fresh seed without chat_created). + from chat.db.connection import open_db + + with open_db(tmp_path / "test.db") as conn: + conn.execute("DELETE FROM chats") + conn.commit() + response = client.get("/chats") + assert response.status_code == 200 + body = response.text.lower() + # Empty state should mention there are no chats yet. + assert "no chats yet" in body + + +def test_chats_list_renders_existing_chats(client, tmp_path): + _author_bot_and_chat(tmp_path / "test.db", "bot_a") + + response = client.get("/chats") + assert response.status_code == 200 + body = response.text + # The bot's display name should appear in the chat row. + assert "BotA" in body + # The chat's in-fiction time should appear in the meta. + assert "2026-04-26T20:00:00+00:00" in body + + +def test_existing_template_routes_still_work_with_new_layout(client): + # Smoke test the layout reshuffle didn't break the existing pages. + for path in ("/bots", "/bots/new", "/settings"): + response = client.get(path) + assert response.status_code == 200, f"{path} returned {response.status_code}" + body = response.text + # Each page should now show the persistent left-rail brand link. + assert 'class="rail"' in body or "rail-brand" in body diff --git a/tests/test_chat_shell.py b/tests/test_chat_shell.py new file mode 100644 index 0000000..5cd3577 --- /dev/null +++ b/tests/test_chat_shell.py @@ -0,0 +1,83 @@ +from __future__ import annotations + +from pathlib import Path + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project + + +@pytest.fixture +def client(tmp_path, monkeypatch): + cfg = tmp_path / "config.toml" + cfg.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(cfg)) + db = tmp_path / "test.db" + monkeypatch.setenv("CHAT_DB_PATH", str(db)) + with TestClient(app) as c: + yield c + + +def _seed_chat(db_path: Path, bot_id: str = "bot_a", chat_id: str = "chat_bot_a") -> None: + """Author a bot, create a chat with default state.""" + with open_db(db_path) as conn: + append_event( + conn, + kind="bot_authored", + payload={ + "id": bot_id, + "name": "BotA", + "persona": "...", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "...", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": chat_id, + "host_bot_id": bot_id, + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + project(conn) + + +def test_get_chat_404_when_missing(client): + response = client.get("/chats/no_such_chat") + assert response.status_code == 404 + + +def test_get_chat_renders_shell_with_host_bot_name(client, tmp_path): + _seed_chat(tmp_path / "test.db") + response = client.get("/chats/chat_bot_a") + assert response.status_code == 200 + body = response.text + assert "BotA" in body + assert " None: + with open_db(db) as conn: + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "...", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + # Edge bot_a -> you with affinity_delta=0 to materialise the row at + # default 50/50. + append_event( + conn, + kind="edge_update", + payload={ + "source_id": "bot_a", + "target_id": "you", + "chat_id": "chat_bot_a", + "affinity_delta": 0, + }, + ) + append_event( + conn, + kind="memory_written", + payload={ + "owner_id": "bot_a", + "chat_id": "chat_bot_a", + "pov_summary": "A memory", + "witness_you": 1, + "witness_host": 1, + "witness_guest": 0, + "significance": 1, + }, + ) + project(conn) + + +def test_edit_edge_affinity_emits_manual_edit_and_updates(client, tmp_path): + _seed(tmp_path / "test.db") + response = client.post( + "/chats/chat_bot_a/drawer/edge/bot_a/you/affinity", + data={"affinity": "75"}, + ) + assert response.status_code == 200 # returns refreshed drawer partial + # Refresh shows the new affinity value. + assert "75" in response.text + + with open_db(tmp_path / "test.db") as conn: + cur = conn.execute( + "SELECT payload_json FROM event_log WHERE kind = 'manual_edit'" + ).fetchall() + assert len(cur) == 1 + payload = json.loads(cur[0][0]) + assert payload["target_kind"] == "edge_affinity" + assert payload["prior_value"] == 50 + assert payload["new_value"] == 75 + assert payload["target_id"]["source_id"] == "bot_a" + assert payload["target_id"]["target_id"] == "you" + + from chat.state.edges import get_edge + + edge = get_edge(conn, "bot_a", "you") + assert edge["affinity"] == 75 + + +def test_edit_memory_significance_emits_event(client, tmp_path): + _seed(tmp_path / "test.db") + with open_db(tmp_path / "test.db") as conn: + memory_id = conn.execute("SELECT id FROM memories LIMIT 1").fetchone()[0] + response = client.post( + f"/chats/chat_bot_a/drawer/memory/{memory_id}/significance", + data={"significance": "3"}, + ) + assert response.status_code == 200 + + with open_db(tmp_path / "test.db") as conn: + sig = conn.execute( + "SELECT significance FROM memories WHERE id = ?", (memory_id,) + ).fetchone()[0] + assert sig == 3 + cur = conn.execute( + "SELECT payload_json FROM event_log WHERE kind = 'manual_edit'" + ).fetchall() + assert len(cur) == 1 + payload = json.loads(cur[0][0]) + assert payload["target_kind"] == "memory_significance" + assert payload["prior_value"] == 1 + assert payload["new_value"] == 3 + assert payload["target_id"] == memory_id + + +def test_toggle_memory_pin_manual_emits_event_with_auto_pinned_0(client, tmp_path): + _seed(tmp_path / "test.db") + with open_db(tmp_path / "test.db") as conn: + memory_id = conn.execute("SELECT id FROM memories LIMIT 1").fetchone()[0] + response = client.post( + f"/chats/chat_bot_a/drawer/memory/{memory_id}/pin", + data={"pinned": "1"}, + ) + assert response.status_code == 200 + + with open_db(tmp_path / "test.db") as conn: + row = conn.execute( + "SELECT pinned, auto_pinned FROM memories WHERE id = ?", (memory_id,) + ).fetchone() + assert row[0] == 1 + assert row[1] == 0 # NOT auto-pinned (manual pin survives auto-eviction) + # The pin toggle uses memory_pin_changed (not manual_edit). + cur = conn.execute( + "SELECT payload_json FROM event_log " + "WHERE kind = 'memory_pin_changed' ORDER BY id DESC LIMIT 1" + ).fetchone() + payload = json.loads(cur[0]) + assert payload["pinned"] == 1 + assert payload["auto_pinned"] == 0 + assert payload["memory_id"] == memory_id + + +def test_edit_404_when_chat_missing(client): + response = client.post( + "/chats/no_such/drawer/edge/bot_a/you/affinity", + data={"affinity": "75"}, + ) + assert response.status_code == 404 + + +def test_edit_404_when_target_missing(client, tmp_path): + _seed(tmp_path / "test.db") + response = client.post( + "/chats/chat_bot_a/drawer/memory/99999/significance", + data={"significance": "2"}, + ) + assert response.status_code == 404 diff --git a/tests/test_drawer_render.py b/tests/test_drawer_render.py new file mode 100644 index 0000000..89309d8 --- /dev/null +++ b/tests/test_drawer_render.py @@ -0,0 +1,210 @@ +from __future__ import annotations + +from pathlib import Path + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project + + +@pytest.fixture +def client(tmp_path, monkeypatch): + cfg = tmp_path / "config.toml" + cfg.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(cfg)) + db = tmp_path / "test.db" + monkeypatch.setenv("CHAT_DB_PATH", str(db)) + with TestClient(app) as c: + # Disable background worker (we won't drive turns). + if hasattr(app.state, "background_worker"): + app.state.background_worker.enabled = False + yield c + + +def _seed(db: Path) -> None: + with open_db(db) as conn: + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "...", + "voice_samples": [], + "traits": ["shy"], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + append_event( + conn, + kind="you_authored", + payload={ + "name": "Me", + "pronouns": "they/them", + "persona": "engineer", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + # Activity for both you and host bot. + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": "you", + "posture": "sitting", + "action": {"verb": "thinking"}, + "attention": "the screen", + }, + ) + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": "bot_a", + "posture": "standing", + "action": {"verb": "looking out the window"}, + }, + ) + # Edge host -> you. + append_event( + conn, + kind="edge_update", + payload={ + "source_id": "bot_a", + "target_id": "you", + "chat_id": "chat_bot_a", + "affinity_delta": 5, + "trust_delta": 2, + "knowledge_facts": ["Me likes coffee"], + }, + ) + # A regular memory. + append_event( + conn, + kind="memory_written", + payload={ + "owner_id": "bot_a", + "chat_id": "chat_bot_a", + "pov_summary": "Talked about her sister", + "witness_you": 1, + "witness_host": 1, + "witness_guest": 0, + "significance": 2, + }, + ) + # A pinned memory with significance 3 (★★). + append_event( + conn, + kind="memory_written", + payload={ + "owner_id": "bot_a", + "chat_id": "chat_bot_a", + "pov_summary": "First kiss", + "witness_you": 1, + "witness_host": 1, + "witness_guest": 0, + "significance": 3, + "pinned": 1, + "auto_pinned": 1, + }, + ) + project(conn) + + +def test_drawer_404_when_chat_missing(client): + response = client.get("/chats/no_such/drawer") + assert response.status_code == 404 + + +def test_drawer_renders_scene_and_activity(client, tmp_path): + _seed(tmp_path / "test.db") + response = client.get("/chats/chat_bot_a/drawer") + assert response.status_code == 200 + body = response.text + # Scene/time anchor. + assert "2026-04-26" in body + # Activity verbs from both entities. + assert "thinking" in body + assert "looking out the window" in body + # Activity attention. + assert "the screen" in body + + +def test_drawer_renders_edges(client, tmp_path): + _seed(tmp_path / "test.db") + response = client.get("/chats/chat_bot_a/drawer") + assert response.status_code == 200 + body = response.text + assert "BotA" in body + assert "you" in body + # Default affinity 50 + delta 5 = 55. + assert "55" in body + # Knowledge fact appears. + assert "Me likes coffee" in body + + +def test_drawer_renders_memories_with_significance_markers(client, tmp_path): + _seed(tmp_path / "test.db") + response = client.get("/chats/chat_bot_a/drawer") + assert response.status_code == 200 + body = response.text + assert "Talked about her sister" in body + assert "First kiss" in body + # Pinned counter shows 1 / 8 (or 1/8). + assert "1 / 8" in body or "1/8" in body + # Significance star marker for the pinned, score-3 memory. + assert "★" in body + + +def test_drawer_handles_no_state_gracefully(client, tmp_path): + db = tmp_path / "test.db" + with open_db(db) as conn: + # Just enough state for the chat to exist. + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "...", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + project(conn) + response = client.get("/chats/chat_bot_a/drawer") + assert response.status_code == 200 + body = response.text + # Drawer renders gracefully with empty placeholders. + assert "No active container" in body or "Container:" not in body + assert "No edges yet" in body or "Edges" in body diff --git a/tests/test_edges.py b/tests/test_edges.py new file mode 100644 index 0000000..22746fc --- /dev/null +++ b/tests/test_edges.py @@ -0,0 +1,162 @@ +from chat.db.migrate import apply_migrations +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.state.edges import get_edge, list_edges_for +import chat.state.entities # registers bot/you handlers +import chat.state.edges # registers edge_update handler + + +def _seed_entities(conn) -> None: + append_event(conn, kind="bot_authored", payload={ + "id": "bot_a", "name": "BotA", "persona": "p", + "voice_samples": [], "traits": [], + "backstory": "", "initial_relationship_to_you": "", + "kickoff_prose": "", + }) + append_event(conn, kind="you_authored", payload={ + "name": "Me", "pronouns": "", "persona": "", + }) + + +def test_edge_update_upsert_applies_first_delta(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_entities(conn) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "affinity_delta": 5, + }) + project(conn) + edge = get_edge(conn, "bot_a", "you") + assert edge is not None + assert edge["affinity"] == 55 + assert edge["trust"] == 50 + assert edge["knowledge"] == [] + assert edge["summary"] == "" + + +def test_edge_update_multiple_deltas_accumulate(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_entities(conn) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "affinity_delta": 5, + }) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "affinity_delta": -3, + "trust_delta": 2, + "knowledge_facts": ["she has a sister"], + }) + project(conn) + edge = get_edge(conn, "bot_a", "you") + assert edge is not None + assert edge["affinity"] == 52 + assert edge["trust"] == 52 + assert edge["knowledge"] == ["she has a sister"] + + +def test_edge_update_clamps_affinity_at_max(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_entities(conn) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "affinity_delta": 5, + }) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "affinity_delta": 100, + }) + project(conn) + edge = get_edge(conn, "bot_a", "you") + assert edge is not None + assert edge["affinity"] == 100 + + +def test_edge_update_clamps_trust_at_min(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_entities(conn) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "trust_delta": -200, + }) + project(conn) + edge = get_edge(conn, "bot_a", "you") + assert edge is not None + assert edge["trust"] == 0 + + +def test_edges_are_directed_and_asymmetric(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_entities(conn) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "affinity_delta": 5, + }) + append_event(conn, kind="edge_update", payload={ + "source_id": "you", "target_id": "bot_a", + "affinity_delta": 10, + }) + project(conn) + forward = get_edge(conn, "bot_a", "you") + reverse = get_edge(conn, "you", "bot_a") + assert forward is not None and reverse is not None + assert forward["affinity"] == 55 + assert reverse["affinity"] == 60 + # Independent rows + assert forward["affinity"] != reverse["affinity"] + + +def test_edge_update_bumps_last_interaction(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_entities(conn) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", + "affinity_delta": 1, + "last_interaction_at": "2026-04-26T10:00:00", + "last_interaction_chat_id": "chat_bot_a", + }) + project(conn) + edge = get_edge(conn, "bot_a", "you") + assert edge is not None + assert edge["last_interaction_at"] == "2026-04-26T10:00:00" + assert edge["last_interaction_chat_id"] == "chat_bot_a" + + +def test_list_edges_for_returns_outgoing_only(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_entities(conn) + append_event(conn, kind="bot_authored", payload={ + "id": "bot_b", "name": "BotB", "persona": "p", + "voice_samples": [], "traits": [], + "backstory": "", "initial_relationship_to_you": "", + "kickoff_prose": "", + }) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "you", "affinity_delta": 1, + }) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", "target_id": "bot_b", "affinity_delta": 2, + }) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_b", "target_id": "bot_a", "affinity_delta": 3, + }) + project(conn) + outgoing = list_edges_for(conn, "bot_a") + targets = [e["target_id"] for e in outgoing] + assert targets == sorted(targets) + assert set(targets) == {"you", "bot_b"} diff --git a/tests/test_entities.py b/tests/test_entities.py new file mode 100644 index 0000000..5ef6f17 --- /dev/null +++ b/tests/test_entities.py @@ -0,0 +1,38 @@ +from chat.db.migrate import apply_migrations +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.state.entities import get_bot, list_bots, get_you +import chat.state.entities # registers handlers + + +def test_bot_authored_creates_bot_row(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="bot_authored", payload={ + "id": "bot_a", "name": "BotA", + "persona": "...", "voice_samples": ["sample"], "traits": ["shy"], + "backstory": "...", + "initial_relationship_to_you": "coworker", + "kickoff_prose": "you stay late", + }) + project(conn) + bot = get_bot(conn, "bot_a") + assert bot is not None + assert bot["name"] == "BotA" + assert bot["traits"] == ["shy"] + assert "bot_a" in [b["id"] for b in list_bots(conn)] + + +def test_you_authored_creates_you_singleton(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="you_authored", payload={ + "name": "Me", "pronouns": "they/them", "persona": "engineer", + }) + project(conn) + you = get_you(conn) + assert you is not None + assert you["name"] == "Me" diff --git a/tests/test_error_ux.py b/tests/test_error_ux.py new file mode 100644 index 0000000..d30139f --- /dev/null +++ b/tests/test_error_ux.py @@ -0,0 +1,57 @@ +from __future__ import annotations + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app + + +@pytest.fixture +def client(tmp_path, monkeypatch): + cfg = tmp_path / "config.toml" + cfg.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(cfg)) + db = tmp_path / "test.db" + monkeypatch.setenv("CHAT_DB_PATH", str(db)) + with TestClient(app) as c: + if hasattr(app.state, "background_worker"): + app.state.background_worker.enabled = False + yield c + + +def _setup_minimal_state(db_path): + """Set up enough state so the first-run middleware doesn't redirect.""" + from chat.db.connection import open_db + from chat.eventlog.log import append_event + from chat.eventlog.projector import project + + with open_db(db_path) as conn: + append_event( + conn, + kind="you_authored", + payload={"name": "Me", "pronouns": "", "persona": ""}, + ) + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + project(conn) + + +def test_404_renders_friendly_page_for_html(client, tmp_path): + _setup_minimal_state(tmp_path / "test.db") + response = client.get("/chats/no_such_chat") + assert response.status_code == 404 + body = response.text + assert "404" in body + assert "back to" in body.lower() diff --git a/tests/test_eventlog.py b/tests/test_eventlog.py new file mode 100644 index 0000000..c7c129f --- /dev/null +++ b/tests/test_eventlog.py @@ -0,0 +1,15 @@ +from chat.db.migrate import apply_migrations +from chat.db.connection import open_db +from chat.eventlog.log import append_event, read_events + + +def test_append_and_read(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + eid = append_event(conn, kind="test_kind", payload={"a": 1}) + assert eid > 0 + rows = list(read_events(conn)) + assert len(rows) == 1 + assert rows[0].kind == "test_kind" + assert rows[0].payload["a"] == 1 diff --git a/tests/test_first_run.py b/tests/test_first_run.py new file mode 100644 index 0000000..c7799aa --- /dev/null +++ b/tests/test_first_run.py @@ -0,0 +1,146 @@ +from __future__ import annotations + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project + + +@pytest.fixture +def client(tmp_path, monkeypatch): + cfg = tmp_path / "config.toml" + cfg.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(cfg)) + db = tmp_path / "test.db" + monkeypatch.setenv("CHAT_DB_PATH", str(db)) + with TestClient(app) as c: + if hasattr(app.state, "background_worker"): + app.state.background_worker.enabled = False + yield c + + +def test_root_redirects_to_settings_when_no_you(client): + response = client.get("/", follow_redirects=False) + assert response.status_code == 303 + assert response.headers["location"] == "/settings" + + +def test_chats_redirects_to_settings_when_no_you(client): + response = client.get("/chats", follow_redirects=False) + assert response.status_code == 303 + assert response.headers["location"] == "/settings" + + +def test_redirects_to_bots_new_when_you_exists_but_no_bots(client, tmp_path): + with open_db(tmp_path / "test.db") as conn: + append_event( + conn, + kind="you_authored", + payload={ + "name": "Me", + "pronouns": "they/them", + "persona": "engineer", + }, + ) + project(conn) + response = client.get("/chats", follow_redirects=False) + assert response.status_code == 303 + assert response.headers["location"] == "/bots/new" + + +def test_root_redirects_to_bots_new_when_you_exists_but_no_bots(client, tmp_path): + with open_db(tmp_path / "test.db") as conn: + append_event( + conn, + kind="you_authored", + payload={ + "name": "Me", + "pronouns": "they/them", + "persona": "engineer", + }, + ) + project(conn) + response = client.get("/", follow_redirects=False) + assert response.status_code == 303 + assert response.headers["location"] == "/bots/new" + + +def test_no_redirect_when_setup_complete(client, tmp_path): + with open_db(tmp_path / "test.db") as conn: + append_event( + conn, + kind="you_authored", + payload={ + "name": "Me", + "pronouns": "they/them", + "persona": "engineer", + }, + ) + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "...", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + project(conn) + response = client.get("/chats", follow_redirects=False) + # /chats page renders normally (200) instead of redirecting. + assert response.status_code == 200 + + +def test_settings_page_accessible_without_you(client): + """Don't redirect FROM /settings — user needs to fill it out.""" + response = client.get("/settings", follow_redirects=False) + assert response.status_code == 200 + + +def test_bots_new_accessible_without_redirect(client, tmp_path): + with open_db(tmp_path / "test.db") as conn: + append_event( + conn, + kind="you_authored", + payload={"name": "Me", "pronouns": "", "persona": ""}, + ) + project(conn) + response = client.get("/bots/new", follow_redirects=False) + assert response.status_code == 200 + + +def test_bots_list_accessible_without_redirect_when_empty(client, tmp_path): + """The bot list page itself should never redirect — even when empty.""" + with open_db(tmp_path / "test.db") as conn: + append_event( + conn, + kind="you_authored", + payload={"name": "Me", "pronouns": "", "persona": ""}, + ) + project(conn) + response = client.get("/bots", follow_redirects=False) + assert response.status_code == 200 + + +def test_post_to_settings_not_redirected(client): + """POST should bypass middleware — it's a write, not a landing nav.""" + response = client.post( + "/settings", + data={"name": "Me", "pronouns": "", "persona": ""}, + follow_redirects=False, + ) + # Settings POST returns 200 with the saved page (no HTTPException raised). + assert response.status_code == 200 + + +def test_health_endpoint_not_redirected(client): + response = client.get("/health", follow_redirects=False) + assert response.status_code == 200 diff --git a/tests/test_health.py b/tests/test_health.py new file mode 100644 index 0000000..f44ad32 --- /dev/null +++ b/tests/test_health.py @@ -0,0 +1,9 @@ +from fastapi.testclient import TestClient +from chat.app import app + + +def test_health_endpoint_returns_ok(): + client = TestClient(app) + response = client.get("/health") + assert response.status_code == 200 + assert response.json() == {"status": "ok"} diff --git a/tests/test_kickoff.py b/tests/test_kickoff.py new file mode 100644 index 0000000..4efa2a7 --- /dev/null +++ b/tests/test_kickoff.py @@ -0,0 +1,142 @@ +import json +import pytest + +from chat.llm.mock import MockLLMClient +from chat.services.kickoff import ( + ActivityShape, + KickoffParse, + parse_kickoff, +) + + +def _full_kickoff_json() -> str: + return json.dumps( + { + "container_name": "office bullpen, late evening", + "container_type": "office", + "container_properties": { + "moving": False, + "public": False, + "audible_range": "room", + }, + "you_activity": { + "posture": "sitting at your desk", + "action_verb": "finishing emails", + "action_interruptible": True, + "action_required_attention": "low", + "action_expected_duration": "15m", + "attention": "the screen", + "holding": ["coffee mug"], + }, + "bot_activity": { + "posture": "sitting at her desk", + "action_verb": "pretending to work", + "action_interruptible": True, + "action_required_attention": "low", + "action_expected_duration": "indefinite", + "attention": "you, in glances", + "holding": [], + }, + "initial_time_iso": "2026-04-26T19:42:00", + "edge_seed_summary": "coworkers; aware of each other; no shared history beyond the office", + "edge_seed_knowledge_facts": [ + "they work on the same floor", + "it is unusual to be the only two left", + ], + } + ) + + +@pytest.mark.asyncio +async def test_parse_kickoff_happy_path_populates_fields(): + mock = MockLLMClient(canned=[_full_kickoff_json()]) + result = await parse_kickoff( + mock, + model="m", + bot_name="BotA", + bot_persona="reserved colleague who quietly notices things", + initial_relationship_to_you="coworker, slight crush, never voiced", + kickoff_prose=( + "you stay late at the office; only you and BotA are there; " + "she's at her desk pretending to work" + ), + you_name="You", + ) + assert isinstance(result, KickoffParse) + assert result.container_name == "office bullpen, late evening" + assert result.container_type == "office" + assert isinstance(result.you_activity, ActivityShape) + assert result.you_activity.posture == "sitting at your desk" + assert result.bot_activity.action_verb == "pretending to work" + assert result.edge_seed_summary.startswith("coworkers") + assert "they work on the same floor" in result.edge_seed_knowledge_facts + assert result.initial_time_iso == "2026-04-26T19:42:00" + + +@pytest.mark.asyncio +async def test_parse_kickoff_applies_activity_defaults_for_missing_fields(): + minimal_payload = { + "container_name": "kitchen", + "container_type": "kitchen", + "container_properties": {}, + "you_activity": { + "posture": "standing", + "action_verb": "boiling water", + "action_interruptible": True, + "action_required_attention": "low", + "action_expected_duration": "5m", + }, + "bot_activity": { + "posture": "leaning on the counter", + "action_verb": "scrolling phone", + "action_interruptible": True, + "action_required_attention": "low", + "action_expected_duration": "10m", + }, + "initial_time_iso": "2026-04-26T08:00:00", + "edge_seed_summary": "roommates", + "edge_seed_knowledge_facts": [], + } + mock = MockLLMClient(canned=[json.dumps(minimal_payload)]) + result = await parse_kickoff( + mock, + model="m", + bot_name="BotA", + bot_persona="laid-back roommate", + initial_relationship_to_you="roommates of two years", + kickoff_prose="morning in the kitchen; you're making tea while BotA scrolls her phone", + you_name="You", + ) + assert result.you_activity.attention == "" + assert result.you_activity.holding == [] + assert result.bot_activity.attention == "" + assert result.bot_activity.holding == [] + # mutating one default must not leak into the other (default_factory check) + result.you_activity.holding.append("kettle") + assert result.bot_activity.holding == [] + + +@pytest.mark.asyncio +async def test_parse_kickoff_falls_back_to_empty_when_classifier_fails(): + """When the classifier fails three times, return an empty KickoffParse + instead of raising — the confirm form lets the user fill in by hand. + """ + mock = MockLLMClient(canned=["nope", "still nope", "still bad"]) + result = await parse_kickoff( + mock, + model="m", + bot_name="BotA", + bot_persona="x", + initial_relationship_to_you="y", + kickoff_prose="z", + you_name="You", + ) + assert isinstance(result, KickoffParse) + assert result.container_name == "" + assert result.container_type == "" + assert result.edge_seed_summary == "" + assert result.edge_seed_knowledge_facts == [] + # Activity defaults sane (action_interruptible defaults to True so the + # confirm form's checkbox is in a reasonable initial state). + assert result.you_activity.action_interruptible is True + assert result.bot_activity.action_interruptible is True diff --git a/tests/test_kickoff_confirm.py b/tests/test_kickoff_confirm.py new file mode 100644 index 0000000..ef308cb --- /dev/null +++ b/tests/test_kickoff_confirm.py @@ -0,0 +1,212 @@ +from __future__ import annotations + +import json +from pathlib import Path + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.llm.mock import MockLLMClient + + +CANNED_PARSE = { + "container_name": "office", + "container_type": "workplace", + "container_properties": { + "public": True, + "moving": False, + "audible_range": "normal", + }, + "you_activity": { + "posture": "sitting", + "action_verb": "working late", + "action_interruptible": True, + "action_required_attention": "medium", + "action_expected_duration": "an hour", + "attention": "the screen", + "holding": [], + }, + "bot_activity": { + "posture": "sitting", + "action_verb": "writing email", + "action_interruptible": True, + "action_required_attention": "medium", + "action_expected_duration": "a few minutes", + "attention": "her keyboard", + "holding": [], + }, + "initial_time_iso": "2026-04-26T20:00:00+00:00", + "edge_seed_summary": "BotA is your coworker.", + "edge_seed_knowledge_facts": [ + "coworker", + "they sometimes stay late together", + ], +} + + +@pytest.fixture +def client(tmp_path, monkeypatch): + config_path = tmp_path / "config.toml" + config_path.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(config_path)) + monkeypatch.setenv("CHAT_DB_PATH", str(tmp_path / "test.db")) + + # Import after env is set so dependency lookup uses MockLLMClient. + from chat.web.kickoff import get_llm_client + + mock = MockLLMClient(canned=[json.dumps(CANNED_PARSE)]) + app.dependency_overrides[get_llm_client] = lambda: mock + + with TestClient(app) as c: + c.mock_llm = mock # type: ignore[attr-defined] + yield c + + app.dependency_overrides.clear() + + +def _author_bot(db_path: Path, bot_id: str = "bot_a") -> None: + from chat.db.connection import open_db + + with open_db(db_path) as conn: + append_event( + conn, + kind="bot_authored", + payload={ + "id": bot_id, + "name": "BotA", + "persona": "thoughtful, observant", + "voice_samples": [], + "traits": ["shy"], + "backstory": "", + "initial_relationship_to_you": "coworker", + "kickoff_prose": "you stay late at the office; she's there too", + }, + ) + project(conn) + + +def test_get_kickoff_404_when_bot_missing(client): + response = client.get("/bots/no_such_bot/kickoff") + assert response.status_code == 404 + + +def test_get_kickoff_renders_parsed_form(client, tmp_path): + _author_bot(tmp_path / "test.db", "bot_a") + response = client.get("/bots/bot_a/kickoff") + assert response.status_code == 200 + body = response.text + assert "office" in body + assert "sitting" in body + assert "working late" in body + # Mock was consumed once. + assert len(client.mock_llm._canned) == 0 + + +def test_post_kickoff_creates_chat_and_redirects(client, tmp_path): + _author_bot(tmp_path / "test.db", "bot_a") + + form_data = { + "container_name": "office", + "container_type": "workplace", + "container_properties": json.dumps(CANNED_PARSE["container_properties"]), + "initial_time_iso": "2026-04-26T20:00:00+00:00", + "you_activity_posture": "sitting", + "you_activity_action_verb": "working late", + "you_activity_action_interruptible": "on", + "you_activity_action_required_attention": "medium", + "you_activity_action_expected_duration": "an hour", + "you_activity_attention": "the screen", + "you_activity_holding": "", + "bot_activity_posture": "sitting", + "bot_activity_action_verb": "writing email", + "bot_activity_action_interruptible": "on", + "bot_activity_action_required_attention": "medium", + "bot_activity_action_expected_duration": "a few minutes", + "bot_activity_attention": "her keyboard", + "bot_activity_holding": "", + "edge_seed_summary": "BotA is your coworker.", + "edge_seed_knowledge_facts": "coworker\nthey sometimes stay late together", + } + response = client.post( + "/bots/bot_a/kickoff", + data=form_data, + follow_redirects=False, + ) + assert response.status_code == 303 + assert response.headers["location"] == "/chats/chat_bot_a" + + from chat.db.connection import open_db + from chat.state.world import ( + active_scene, + find_container, + get_activity, + get_chat, + ) + from chat.state.edges import get_edge + + with open_db(tmp_path / "test.db") as conn: + chat = get_chat(conn, "chat_bot_a") + assert chat is not None + assert chat["host_bot_id"] == "bot_a" + assert chat["time"] == "2026-04-26T20:00:00+00:00" + + container = find_container(conn, "chat_bot_a", "office") + assert container is not None + assert container["type"] == "workplace" + + you_act = get_activity(conn, "you") + assert you_act is not None + assert you_act["posture"] == "sitting" + assert you_act["action"]["verb"] == "working late" + + bot_act = get_activity(conn, "bot_a") + assert bot_act is not None + assert bot_act["posture"] == "sitting" + assert bot_act["action"]["verb"] == "writing email" + + scene = active_scene(conn, "chat_bot_a") + assert scene is not None + assert scene["ended_at"] is None + assert "you" in scene["participants"] + assert "bot_a" in scene["participants"] + + edge = get_edge(conn, "bot_a", "you") + assert edge is not None + knowledge = edge["knowledge"] + assert "coworker" in knowledge + assert "they sometimes stay late together" in knowledge + # The seed summary should appear somewhere in knowledge as a v1 compromise. + assert any("BotA is your coworker" in k for k in knowledge) + + +def test_post_kickoff_404_when_bot_missing(client): + response = client.post( + "/bots/no_such/kickoff", + data={ + "container_name": "office", + "container_type": "workplace", + "container_properties": "{}", + "initial_time_iso": "2026-04-26T20:00:00+00:00", + "you_activity_posture": "", + "you_activity_action_verb": "", + "you_activity_action_interruptible": "on", + "you_activity_action_required_attention": "low", + "you_activity_action_expected_duration": "", + "you_activity_attention": "", + "you_activity_holding": "", + "bot_activity_posture": "", + "bot_activity_action_verb": "", + "bot_activity_action_interruptible": "on", + "bot_activity_action_required_attention": "low", + "bot_activity_action_expected_duration": "", + "bot_activity_attention": "", + "bot_activity_holding": "", + "edge_seed_summary": "", + "edge_seed_knowledge_facts": "", + }, + follow_redirects=False, + ) + assert response.status_code == 404 diff --git a/tests/test_llm_mock.py b/tests/test_llm_mock.py new file mode 100644 index 0000000..d56a783 --- /dev/null +++ b/tests/test_llm_mock.py @@ -0,0 +1,21 @@ +import pytest +from chat.llm.mock import MockLLMClient +from chat.llm.client import Message + + +@pytest.mark.asyncio +async def test_mock_returns_canned_response(): + client = MockLLMClient(canned=["Hello, world."]) + msgs = [Message(role="user", content="hi")] + out = await client.generate(msgs, model="any") + assert out == "Hello, world." + + +@pytest.mark.asyncio +async def test_mock_streams_tokens(): + client = MockLLMClient(canned=["abcd"]) + msgs = [Message(role="user", content="hi")] + chunks = [] + async for chunk in client.stream(msgs, model="any"): + chunks.append(chunk) + assert "".join(chunks) == "abcd" diff --git a/tests/test_memory.py b/tests/test_memory.py new file mode 100644 index 0000000..3675ce6 --- /dev/null +++ b/tests/test_memory.py @@ -0,0 +1,229 @@ +from __future__ import annotations +import pytest + +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +import chat.state.memory # registers memory_written handler +from chat.state.memory import get_memory, get_pinned, search_memories + + +def _base_memory(**overrides): + payload = { + "owner_id": "bot_a", + "chat_id": "chat_bot_a", + "scene_id": 1, + "pov_summary": "She laughed at his joke about owls.", + "witness_you": 1, + "witness_host": 1, + "witness_guest": 0, + "chat_clock_at": "2026-04-26T10:00:00", + "source": "direct", + "reliability": 1.0, + "significance": 1, + "pinned": 0, + "auto_pinned": 0, + } + payload.update(overrides) + return payload + + +def test_memory_written_is_projected_and_readable(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory()) + project(conn) + row = conn.execute("SELECT id FROM memories").fetchone() + assert row is not None + mem = get_memory(conn, row[0]) + assert mem is not None + assert mem["owner_id"] == "bot_a" + assert mem["chat_id"] == "chat_bot_a" + assert mem["scene_id"] == 1 + assert mem["pov_summary"] == "She laughed at his joke about owls." + assert mem["witness_you"] == 1 + assert mem["witness_host"] == 1 + assert mem["witness_guest"] == 0 + assert mem["chat_clock_at"] == "2026-04-26T10:00:00" + assert mem["source"] == "direct" + assert mem["reliability"] == 1.0 + assert mem["significance"] == 1 + assert mem["pinned"] == 0 + assert mem["auto_pinned"] == 0 + + +def test_get_memory_returns_none_for_missing_id(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + assert get_memory(conn, 9999) is None + + +def test_search_memories_filters_out_non_witness(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary="The cat sat on the mat.", + witness_you=1, witness_host=1, witness_guest=0, + )) + project(conn) + # guest did not witness => excluded + results = search_memories(conn, "bot_a", "guest", "cat") + assert results == [] + + +def test_search_memories_includes_witnesses(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary="The cat sat on the mat.", + witness_you=1, witness_host=1, witness_guest=0, + )) + project(conn) + results = search_memories(conn, "bot_a", "host", "cat") + assert len(results) == 1 + assert results[0]["pov_summary"] == "The cat sat on the mat." + assert "fts_rank" in results[0] + + +def test_search_memories_fts_matches_only_relevant_text(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary="She loves owls and stars.", + )) + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary="He fixed the broken kettle.", + )) + project(conn) + results = search_memories(conn, "bot_a", "you", "owls") + assert len(results) == 1 + assert results[0]["pov_summary"] == "She loves owls and stars." + + +def test_search_memories_filters_by_owner(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory( + owner_id="bot_a", + pov_summary="Owls hooted at midnight.", + )) + append_event(conn, kind="memory_written", payload=_base_memory( + owner_id="bot_b", + pov_summary="Owls hooted at midnight.", + )) + project(conn) + results_a = search_memories(conn, "bot_a", "you", "owls") + results_b = search_memories(conn, "bot_b", "you", "owls") + assert len(results_a) == 1 + assert results_a[0]["owner_id"] == "bot_a" + assert len(results_b) == 1 + assert results_b[0]["owner_id"] == "bot_b" + + +def test_search_memories_returns_empty_on_no_match(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary="The cat sat on the mat.", + )) + project(conn) + results = search_memories(conn, "bot_a", "you", "spaceship") + assert results == [] + + +def test_search_memories_invalid_witness_role_raises(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + with pytest.raises(ValueError): + search_memories(conn, "bot_a", "everyone", "cat") + + +def test_search_memories_respects_k_limit(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + for i in range(6): + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary=f"Owls hooted at midnight number {i}.", + )) + project(conn) + results = search_memories(conn, "bot_a", "you", "owls", k=4) + assert len(results) == 4 + + +def test_get_pinned_returns_only_pinned(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary="Pinned moment.", + pinned=1, + )) + append_event(conn, kind="memory_written", payload=_base_memory( + pov_summary="Unpinned moment.", + pinned=0, + )) + project(conn) + pinned = get_pinned(conn, "bot_a") + assert len(pinned) == 1 + assert pinned[0]["pov_summary"] == "Pinned moment." + assert pinned[0]["pinned"] == 1 + + +def test_get_pinned_filters_by_owner(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload=_base_memory( + owner_id="bot_a", pov_summary="A's pin.", pinned=1, + )) + append_event(conn, kind="memory_written", payload=_base_memory( + owner_id="bot_b", pov_summary="B's pin.", pinned=1, + )) + project(conn) + pinned_a = get_pinned(conn, "bot_a") + assert len(pinned_a) == 1 + assert pinned_a[0]["owner_id"] == "bot_a" + + +def test_memory_payload_defaults_when_optional_missing(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + append_event(conn, kind="memory_written", payload={ + "owner_id": "bot_a", + "chat_id": "chat_bot_a", + "pov_summary": "Bare minimum memory.", + "witness_you": 1, + "witness_host": 1, + "witness_guest": 1, + }) + project(conn) + row = conn.execute("SELECT id FROM memories").fetchone() + mem = get_memory(conn, row[0]) + assert mem["scene_id"] is None + assert mem["chat_clock_at"] is None + assert mem["source"] == "direct" + assert mem["reliability"] == 1.0 + assert mem["significance"] == 1 + assert mem["pinned"] == 0 + assert mem["auto_pinned"] == 0 + + +def test_schema_version_after_migration_is_at_least_6(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + row = conn.execute( + "SELECT value FROM meta WHERE key = 'schema_version'" + ).fetchone() + assert int(row[0]) >= 6 diff --git a/tests/test_memory_search.py b/tests/test_memory_search.py new file mode 100644 index 0000000..dad7e84 --- /dev/null +++ b/tests/test_memory_search.py @@ -0,0 +1,127 @@ +"""Task 23: FTS5 memory retrieval with witness filter and ranking boosts. + +Verifies that ``search_memories`` applies recency + significance boosts on top +of the FTS5 BM25 rank so that newer / more significant memories surface above +older / less significant ones for the same match. Existing T8 behaviour +(witness filter, k limit, FTS match, role validation) is exercised again here +to lock the contract. +""" + +from __future__ import annotations +import pytest + +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.state.memory import search_memories +import chat.state.memory # noqa: F401 (registers memory_written handler) + + +def _seed(db, *, memory_specs): + """Apply migrations + project a list of memory_written events. + + memory_specs: list of dicts. Required key: ``pov_summary``. Optional keys + override the defaults below. + """ + apply_migrations(db) + with open_db(db) as conn: + for spec in memory_specs: + payload = { + "owner_id": spec.get("owner_id", "bot_a"), + "chat_id": spec.get("chat_id", "chat_bot_a"), + "pov_summary": spec["pov_summary"], + "witness_you": spec.get("witness_you", 1), + "witness_host": spec.get("witness_host", 1), + "witness_guest": spec.get("witness_guest", 0), + "source": "direct", + "reliability": 1.0, + "significance": spec.get("significance", 1), + "pinned": 0, + "auto_pinned": 0, + } + append_event(conn, kind="memory_written", payload=payload) + project(conn) + + +def test_search_filters_by_witness_bit(tmp_path): + db = tmp_path / "t.db" + _seed( + db, + memory_specs=[ + { + "pov_summary": "BotA mentioned her sister", + "witness_you": 1, + "witness_host": 1, + "witness_guest": 0, + }, + ], + ) + with open_db(db) as conn: + # Witnessed by host -> returned. + out = search_memories(conn, "bot_a", "host", "sister", k=4) + assert len(out) == 1 + # NOT witnessed by guest -> filtered out. + out = search_memories(conn, "bot_a", "guest", "sister", k=4) + assert out == [] + + +def test_search_higher_significance_ranks_above_lower(tmp_path): + db = tmp_path / "t.db" + _seed( + db, + memory_specs=[ + # Both match "promise"; the third row carries significance 3 and + # should outrank the first two, which carry the default of 1. + {"pov_summary": "small promise"}, + {"pov_summary": "huge promise"}, + {"pov_summary": "tiny promise", "significance": 3}, + ], + ) + with open_db(db) as conn: + out = search_memories(conn, "bot_a", "host", "promise", k=3) + assert len(out) == 3 + assert out[0]["pov_summary"] == "tiny promise" + assert out[0]["significance"] == 3 + + +def test_search_newer_memory_ranks_above_older_when_same_match(tmp_path): + db = tmp_path / "t.db" + _seed( + db, + memory_specs=[ + {"pov_summary": "BotA said hello"}, + {"pov_summary": "BotA said hello again"}, + ], + ) + with open_db(db) as conn: + out = search_memories(conn, "bot_a", "host", "hello", k=2) + assert len(out) == 2 + # Newer (higher id, "again") wins on the recency boost when the BM25 + # rank and significance are otherwise comparable. + assert out[0]["pov_summary"] == "BotA said hello again" + + +def test_search_respects_k_limit(tmp_path): + db = tmp_path / "t.db" + _seed( + db, + memory_specs=[ + {"pov_summary": "the cat sat"}, + {"pov_summary": "the cat ran"}, + {"pov_summary": "the cat slept"}, + {"pov_summary": "the cat ate"}, + {"pov_summary": "the cat purred"}, + ], + ) + with open_db(db) as conn: + out = search_memories(conn, "bot_a", "host", "cat", k=2) + assert len(out) == 2 + + +def test_search_invalid_witness_role_raises(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + with pytest.raises(ValueError): + search_memories(conn, "bot_a", "invalid_role", "anything", k=4) diff --git a/tests/test_memory_write.py b/tests/test_memory_write.py new file mode 100644 index 0000000..aa87610 --- /dev/null +++ b/tests/test_memory_write.py @@ -0,0 +1,297 @@ +"""Per-turn memory writes (T21). + +After ``assistant_turn`` lands the turn flow records a ``memory_written`` +event for each present POV owner. Phase 1 single-bot turns only have the +host bot as a memory-store owner — ``you`` doesn't have a memory store in +v1 — so we write exactly one row per turn with witness flags +``[you=1, host=1, guest=0]``. The ``pov_summary`` is the assistant's raw +narrative text; T27 rewrites at scene close into per-POV summary form. +""" + +from __future__ import annotations + +import json +from pathlib import Path + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.llm.mock import MockLLMClient +from chat.services.memory_write import record_turn_memory +import chat.state.entities # noqa: F401 - register handlers +import chat.state.memory # noqa: F401 +import chat.state.world # noqa: F401 + + +def _seed_minimal(db_path: Path) -> None: + """Author a bot and create a chat — bare minimum for memory writes.""" + with open_db(db_path) as conn: + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "...", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + project(conn) + + +def test_record_turn_memory_writes_event_and_projects(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + _seed_minimal(db) + with open_db(db) as conn: + eid, mid = record_turn_memory( + conn, + chat_id="chat_bot_a", + host_bot_id="bot_a", + narrative_text="BotA looks up. 'You're back late.'", + scene_id=None, + chat_clock_at="2026-04-26T20:00:00+00:00", + ) + assert eid > 0 + assert mid is not None and mid > 0 + + rows = conn.execute( + "SELECT id, owner_id, chat_id, pov_summary, " + "witness_you, witness_host, witness_guest, " + "source, reliability, significance, pinned, auto_pinned, " + "chat_clock_at " + "FROM memories WHERE owner_id = ?", + ("bot_a",), + ).fetchall() + assert len(rows) == 1 + m = rows[0] + assert m[1] == "bot_a" + assert m[2] == "chat_bot_a" + assert "looks up" in m[3] + assert m[4] == 1 # witness_you + assert m[5] == 1 # witness_host + assert m[6] == 0 # witness_guest + assert m[7] == "direct" + assert m[8] == 1.0 # reliability default + assert m[9] == 1 # significance default + assert m[10] == 0 # pinned default + assert m[11] == 0 # auto_pinned default + assert m[12] == "2026-04-26T20:00:00+00:00" + + # And the underlying event_log row is the canonical source. + cur = conn.execute( + "SELECT COUNT(*) FROM event_log WHERE kind = 'memory_written'" + ) + assert cur.fetchone()[0] == 1 + + +def test_record_turn_memory_omits_optional_fields(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + _seed_minimal(db) + with open_db(db) as conn: + # Call without scene_id/chat_clock_at — should default to None. + eid, mid = record_turn_memory( + conn, + chat_id="chat_bot_a", + host_bot_id="bot_a", + narrative_text="A simple memory.", + ) + assert eid > 0 + assert mid is not None and mid > 0 + + row = conn.execute( + "SELECT scene_id, chat_clock_at, source, reliability, " + "significance, pinned, auto_pinned " + "FROM memories WHERE owner_id = 'bot_a'" + ).fetchone() + assert row is not None + scene_id, chat_clock_at, source, reliability, significance, pinned, auto_pinned = row + assert scene_id is None + assert chat_clock_at is None + assert source == "direct" + assert reliability == 1.0 + assert significance == 1 + assert pinned == 0 + assert auto_pinned == 0 + + +# --------------------------------------------------------------------------- +# Integration: POST /chats//turns produces a memory_written event. +# --------------------------------------------------------------------------- + + +@pytest.fixture +def client(tmp_path, monkeypatch): + cfg = tmp_path / "config.toml" + cfg.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(cfg)) + db = tmp_path / "test.db" + monkeypatch.setenv("CHAT_DB_PATH", str(db)) + + canned_parse = json.dumps( + {"segments": [{"kind": "dialogue", "text": "hello"}]} + ) + canned_response = "BotA nods. 'Hi there.'" + canned_state_update = json.dumps( + {"affinity_delta": 0, "trust_delta": 0, "knowledge_facts": []} + ) + # T26 scene-close detection runs after the state-update pass. ``_seed_full`` + # below doesn't open a scene so the classifier call is short-circuited in + # turns.py — but the canned slot stays in place to document the order. + canned_scene_close = json.dumps( + {"should_close": False, "reason": "no signal"} + ) + + from chat.web.kickoff import get_llm_client + + mock = MockLLMClient( + canned=[ + canned_parse, + canned_response, + canned_state_update, + canned_state_update, + canned_scene_close, + ] + ) + app.dependency_overrides[get_llm_client] = lambda: mock + + with TestClient(app) as c: + # Disable the lifespan-managed background worker — it would try + # to call Featherless with the test API key. The unit tests in + # test_significance.py exercise the worker directly with a mock + # factory; here we only care about the synchronous turn flow. + app.state.background_worker.enabled = False + c.mock_llm = mock # type: ignore[attr-defined] + yield c + + app.dependency_overrides.clear() + + +def _seed_full(db_path: Path) -> None: + """Seed enough state for a full turn flow (matches test_turn_flow.py).""" + with open_db(db_path) as conn: + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "thoughtful, observant", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "...", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + append_event( + conn, + kind="edge_update", + payload={ + "source_id": "bot_a", + "target_id": "you", + "chat_id": "chat_bot_a", + "knowledge_facts": ["coworker"], + }, + ) + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": "you", + "posture": "sitting", + "action": { + "verb": "talking", + "interruptible": True, + "required_attention": "low", + "expected_duration": "ongoing", + }, + "attention": "", + "holding": [], + "status": {}, + }, + ) + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": "bot_a", + "posture": "sitting", + "action": { + "verb": "listening", + "interruptible": True, + "required_attention": "low", + "expected_duration": "ongoing", + }, + "attention": "", + "holding": [], + "status": {}, + }, + ) + project(conn) + + +def test_post_turn_writes_memory_for_host_bot(client, tmp_path): + """After a POST turn, exactly one memory_written event is appended and + a corresponding memory row is projected for the host bot's POV.""" + _seed_full(tmp_path / "test.db") + response = client.post( + "/chats/chat_bot_a/turns", data={"prose": "hello"} + ) + assert response.status_code == 204 + + with open_db(tmp_path / "test.db") as conn: + cur = conn.execute( + "SELECT COUNT(*) FROM event_log WHERE kind = 'memory_written'" + ) + assert cur.fetchone()[0] == 1 + + cur = conn.execute( + "SELECT owner_id, chat_id, pov_summary, " + "witness_you, witness_host, witness_guest, source, significance " + "FROM memories" + ) + rows = cur.fetchall() + assert len(rows) == 1 + owner_id, chat_id, pov_summary, w_you, w_host, w_guest, source, sig = rows[0] + assert owner_id == "bot_a" + assert chat_id == "chat_bot_a" + # pov_summary is the assistant's narrative text (Phase 1 simplification). + assert pov_summary == "BotA nods. 'Hi there.'" + assert w_you == 1 + assert w_host == 1 + assert w_guest == 0 + assert source == "direct" + assert sig == 1 diff --git a/tests/test_migrate.py b/tests/test_migrate.py new file mode 100644 index 0000000..eaafcd3 --- /dev/null +++ b/tests/test_migrate.py @@ -0,0 +1,22 @@ +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations + + +def test_apply_migrations_creates_meta_table(tmp_path): + db = tmp_path / "test.db" + apply_migrations(db) + with open_db(db) as conn: + row = conn.execute( + "SELECT value FROM meta WHERE key = 'schema_version'" + ).fetchone() + assert row is not None + assert int(row[0]) >= 1 + + +def test_apply_migrations_idempotent(tmp_path): + db = tmp_path / "test.db" + apply_migrations(db) + apply_migrations(db) # second call must be a no-op + with open_db(db) as conn: + count = conn.execute("SELECT COUNT(*) FROM meta").fetchone()[0] + assert count == 1 diff --git a/tests/test_per_pov_summary.py b/tests/test_per_pov_summary.py new file mode 100644 index 0000000..3e9d597 --- /dev/null +++ b/tests/test_per_pov_summary.py @@ -0,0 +1,260 @@ +"""Per-POV summary and edge summary update on scene close (T27). + +When a scene closes (via the auto-close path in the turn flow or the +manual button in the drawer), we run a classifier that produces a +per-POV summary for each present witness — Phase 1 single-bot only the +host bot, since "you" doesn't have a memory store in v1. The output +drives three projected updates: + +1. Each ``memories`` row for the closed scene owned by the host bot has + its ``pov_summary`` rewritten via ``manual_edit`` events + (``target_kind="memory_pov_summary"``) so the field carries a proper + scene-level summary instead of the per-turn raw narrative seeded by + T21. +2. The directed bot->you ``edges.summary`` is updated via a new + ``manual_edit`` target_kind ``edge_summary``. v1 strategy combines + the prior summary with the classifier's ``relationship_summary`` + field; the LLM is the one phrasing the merge. +3. Newly-learned facts from the classifier's ``knowledge_facts`` field + are appended via the existing ``edge_update`` event handler. +""" + +from __future__ import annotations + +import json +from pathlib import Path + +import pytest + +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.llm.mock import MockLLMClient +from chat.services.scene_summarize import ( + ScenePOVSummary, + apply_scene_close_summary, + summarize_scene, +) + +# Importing for handler-registration side effects so the freshly-migrated +# DB created in each test below has the projector ready. +import chat.state.edges # noqa: F401 +import chat.state.entities # noqa: F401 +import chat.state.manual_edit # noqa: F401 +import chat.state.memory # noqa: F401 +import chat.state.world # noqa: F401 + + +# --------------------------------------------------------------------------- +# Service-level tests — no FastAPI involvement. +# --------------------------------------------------------------------------- + + +@pytest.mark.asyncio +async def test_summarize_scene_parses_classifier_output(): + canned = json.dumps( + { + "summary": "BotA shared a quiet moment with you in the office.", + "knowledge_facts": ["You like coffee black."], + "relationship_summary": "BotA feels closer to you after this conversation.", + } + ) + mock = MockLLMClient(canned=[canned]) + result = await summarize_scene( + mock, + model="x", + bot_name="BotA", + bot_persona="thoughtful", + you_name="Me", + prior_edge_summary="", + dialogue=[ + {"speaker": "Me", "text": "hi"}, + {"speaker": "BotA", "text": "Hello!"}, + ], + ) + assert isinstance(result, ScenePOVSummary) + assert result.summary.startswith("BotA shared") + assert result.knowledge_facts == ["You like coffee black."] + assert "closer" in result.relationship_summary + + +@pytest.mark.asyncio +async def test_summarize_scene_default_on_failure(): + """Two consecutive non-JSON returns trip the classifier's retry-then-default + path; we should get the empty fallback rather than crashing the close + flow.""" + mock = MockLLMClient(canned=["bad", "still bad", "bad3"]) + result = await summarize_scene( + mock, + model="x", + bot_name="BotA", + bot_persona="", + you_name="Me", + prior_edge_summary="", + dialogue=[], + ) + assert result.summary == "" + assert result.knowledge_facts == [] + assert result.relationship_summary == "" + + +@pytest.mark.asyncio +async def test_apply_scene_close_summary_updates_memories_and_edge(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + canned = json.dumps( + { + "summary": "BotA reassured you about the project deadline.", + "knowledge_facts": ["You are nervous about the deadline."], + "relationship_summary": "BotA showed quiet support.", + } + ) + with open_db(db) as conn: + # Seed bot, you, chat, container, scene, edge, memory, dialogue. + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "...", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + append_event( + conn, + kind="you_authored", + payload={ + "name": "Me", + "pronouns": "they/them", + "persona": "engineer", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + append_event( + conn, + kind="container_created", + payload={ + "chat_id": "chat_bot_a", + "name": "office", + "type": "workplace", + "properties": {}, + }, + ) + append_event( + conn, + kind="scene_opened", + payload={ + "chat_id": "chat_bot_a", + "container_id": 1, + "started_at": "2026-04-26T20:00:00+00:00", + "participants": ["you", "bot_a"], + }, + ) + append_event( + conn, + kind="edge_update", + payload={ + "source_id": "bot_a", + "target_id": "you", + "chat_id": "chat_bot_a", + }, + ) + append_event( + conn, + kind="memory_written", + payload={ + "owner_id": "bot_a", + "chat_id": "chat_bot_a", + "scene_id": 1, + "pov_summary": "Original raw narrative", + "witness_you": 1, + "witness_host": 1, + "witness_guest": 0, + "significance": 1, + }, + ) + append_event( + conn, + kind="user_turn", + payload={ + "chat_id": "chat_bot_a", + "prose": "I'm nervous about the deadline", + "segments": [], + }, + ) + append_event( + conn, + kind="assistant_turn", + payload={ + "chat_id": "chat_bot_a", + "speaker_id": "bot_a", + "text": "It's going to be okay.", + "truncated": False, + "user_turn_id": 1, + }, + ) + project(conn) + + client = MockLLMClient(canned=[canned]) + result = await apply_scene_close_summary( + conn, + client, + classifier_model="x", + chat_id="chat_bot_a", + scene_id=1, + host_bot_id="bot_a", + ) + + # Returned summary plumbs through. + assert "reassured" in result.summary + assert result.knowledge_facts == ["You are nervous about the deadline."] + + # Memory pov_summary updated. + new_pov = conn.execute( + "SELECT pov_summary FROM memories " + "WHERE owner_id = 'bot_a' AND scene_id = 1" + ).fetchone()[0] + assert "reassured" in new_pov + # And the manual_edit event was logged with prior_value capture. + edits = conn.execute( + "SELECT payload_json FROM event_log WHERE kind = 'manual_edit'" + ).fetchall() + assert any( + json.loads(p[0]).get("target_kind") == "memory_pov_summary" + for p in edits + ) + mem_edit = next( + json.loads(p[0]) + for p in edits + if json.loads(p[0]).get("target_kind") == "memory_pov_summary" + ) + assert mem_edit["prior_value"] == "Original raw narrative" + + # Edge summary updated via manual_edit (target_kind="edge_summary"). + from chat.state.edges import get_edge + + edge = get_edge(conn, "bot_a", "you") + assert "support" in edge["summary"] + assert any( + json.loads(p[0]).get("target_kind") == "edge_summary" + for p in edits + ) + + # Knowledge fact appended via edge_update. + assert any("deadline" in fact for fact in edge["knowledge"]) diff --git a/tests/test_prompt.py b/tests/test_prompt.py new file mode 100644 index 0000000..bef8dc0 --- /dev/null +++ b/tests/test_prompt.py @@ -0,0 +1,255 @@ +"""Tests for chat.services.prompt.assemble_narrative_prompt. + +Covers Task 18 — must/should/nice trim tiers (Requirements §3.2) and +the speaker prompt assembly order (§6.3). Tests use direct event-log +seeding so the projector populates state exactly the way the runtime +will at play-time. No LLM is invoked: prompt assembly is deterministic. +""" + +from __future__ import annotations + +import pytest + +from chat.db.connection import open_db +from chat.db.migrate import apply_migrations +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +import chat.state.entities # noqa: F401 (registers handlers) +import chat.state.edges # noqa: F401 +import chat.state.memory # noqa: F401 +import chat.state.world # noqa: F401 +from chat.llm.client import Message +from chat.services.prompt import assemble_narrative_prompt + + +def _seed_basic(conn) -> None: + """Seed bot, you-entity, edge, chat, container, scene, activities.""" + append_event(conn, kind="bot_authored", payload={ + "id": "bot_a", + "name": "Aria", + "persona": "reserved coworker who notices things", + "voice_samples": ["I — sorry, I didn't mean to.", "Right. Of course."], + "traits": ["introverted", "observant"], + "backstory": "An archivist who joined the firm last spring.", + "initial_relationship_to_you": "coworker; mild crush; never voiced", + "kickoff_prose": "you stay late at the office", + }) + append_event(conn, kind="you_authored", payload={ + "name": "Sam", + "pronouns": "they/them", + "persona": "tired analyst", + }) + append_event(conn, kind="chat_created", payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "guest_bot_id": None, + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1 evening", + "weather": "clear", + }) + append_event(conn, kind="container_created", payload={ + "chat_id": "chat_bot_a", + "name": "office bullpen", + "type": "workplace", + "properties": {"public": False, "moving": False, "audible_range": "room"}, + }) + append_event(conn, kind="edge_update", payload={ + "source_id": "bot_a", + "target_id": "you", + "affinity_delta": 12, + "trust_delta": 5, + "knowledge_facts": [ + "they work on the same floor", + "they've stayed late twice this week", + ], + }) + append_event(conn, kind="activity_change", payload={ + "entity_id": "you", + "container_id": 1, + "posture": "sitting at your desk", + "action": {"verb": "finishing emails"}, + "attention": "the screen", + "holding": ["coffee mug"], + }) + append_event(conn, kind="activity_change", payload={ + "entity_id": "bot_a", + "container_id": 1, + "posture": "sitting at her desk", + "action": {"verb": "pretending to work"}, + "attention": "you, in glances", + }) + append_event(conn, kind="scene_opened", payload={ + "chat_id": "chat_bot_a", + "container_id": 1, + "started_at": "2026-04-26T20:00:00+00:00", + "participants": ["you", "bot_a"], + }) + project(conn) + + +def test_basic_assembly_returns_system_message_with_all_must_blocks(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_basic(conn) + msgs = assemble_narrative_prompt( + conn, + chat_id="chat_bot_a", + speaker_bot_id="bot_a", + recent_dialogue=[], + retrieved_memory_summaries=[], + ) + assert isinstance(msgs, list) + assert len(msgs) == 1 + sys_msg = msgs[0] + assert isinstance(sys_msg, Message) + assert sys_msg.role == "system" + body = sys_msg.content + # Must-include markers + assert "Aria" in body + assert "PERSONA" in body + assert "ACTIVITIES" in body + assert "CURRENT SCENE" in body + # Edge to addressee — name + numeric values (default affinity 50, +12 = 62) + assert "Sam" in body + assert "62/100" in body + + +def test_user_turn_appended_as_user_message(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_basic(conn) + msgs = assemble_narrative_prompt( + conn, + chat_id="chat_bot_a", + speaker_bot_id="bot_a", + user_turn_prose="*looks up* Hey.", + recent_dialogue=[], + retrieved_memory_summaries=[], + ) + assert len(msgs) == 2 + assert msgs[0].role == "system" + assert msgs[1].role == "user" + assert msgs[1].content == "*looks up* Hey." + + +def test_must_only_succeeds_with_empty_optional_blocks(tmp_path): + """No dialogue, memories, other edges, or previous scene summary — should not raise.""" + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_basic(conn) + msgs = assemble_narrative_prompt( + conn, + chat_id="chat_bot_a", + speaker_bot_id="bot_a", + recent_dialogue=None, # default → nothing + retrieved_memory_summaries=None, + user_turn_prose=None, + ) + assert len(msgs) == 1 + body = msgs[0].content + # Must blocks present + assert "PERSONA" in body + assert "ACTIVITIES" in body + # Optional blocks not in body (nothing to render) + assert "OTHER EDGES" not in body + assert "PREVIOUS SCENE SUMMARY" not in body + assert "RELEVANT MEMORIES" not in body + + +def test_long_dialogue_keeps_last_4_verbatim_and_summarizes_earlier(tmp_path): + """Stuff a huge dialogue history under budget pressure; older turns + must be elided to a placeholder, the last 4 verbatim, and earlier + unique markers gone. + """ + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_basic(conn) + dialogue = [] + for i in range(20): + speaker = "you" if i % 2 == 0 else "bot_a" + # Each line ~250 tokens of filler => 20 turns ≈ 5000 tokens, + # which together with MUST blocks pushes over soft (1500). + dialogue.append({ + "speaker": speaker, + "text": f"unique-line-marker-{i:02d} " + ("filler " * 200), + }) + msgs = assemble_narrative_prompt( + conn, + chat_id="chat_bot_a", + speaker_bot_id="bot_a", + recent_dialogue=dialogue, + retrieved_memory_summaries=[], + # Soft small enough to force NICE trim but hard fits MUST + 4. + budget_soft=1200, + budget_hard=8000, + ) + body = msgs[0].content + # The last 4 unique markers (16, 17, 18, 19) must be present verbatim. + for i in range(16, 20): + assert f"unique-line-marker-{i:02d}" in body, f"expected last-4 marker {i} in body" + # Older markers must be dropped (replaced by elision placeholder). + for i in range(0, 16): + assert f"unique-line-marker-{i:02d}" not in body + # An "earlier" summary line must be present. + assert "earlier" in body.lower() + # Token count of system message respects hard budget. + import tiktoken + enc = tiktoken.get_encoding("cl100k_base") + assert len(enc.encode(body)) <= 8000 + + +def test_memories_drop_to_top_2_under_budget_pressure(tmp_path): + """4 memory summaries, each large; under tight soft budget only 2 should appear.""" + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_basic(conn) + # Each ~1500 tokens of repeated text; drop tier should kick in. + long_chunk = "alpha beta gamma delta " * 400 + memories = [ + f"MEMORY-A {long_chunk}", + f"MEMORY-B {long_chunk}", + f"MEMORY-C {long_chunk}", + f"MEMORY-D {long_chunk}", + ] + msgs = assemble_narrative_prompt( + conn, + chat_id="chat_bot_a", + speaker_bot_id="bot_a", + recent_dialogue=[], + retrieved_memory_summaries=memories, + # Pressure: budgets that allow MUST + 2 memories but not 4. + budget_soft=4000, + budget_hard=5000, + ) + body = msgs[0].content + # MEMORY-A and MEMORY-B are the top-2 and should remain; C & D dropped. + assert "MEMORY-A" in body + assert "MEMORY-B" in body + assert "MEMORY-C" not in body + assert "MEMORY-D" not in body + # Token count fits the hard budget. + import tiktoken + enc = tiktoken.get_encoding("cl100k_base") + assert len(enc.encode(body)) <= 5000 + + +def test_must_exceeds_budget_hard_raises_value_error(tmp_path): + db = tmp_path / "t.db" + apply_migrations(db) + with open_db(db) as conn: + _seed_basic(conn) + with pytest.raises(ValueError): + assemble_narrative_prompt( + conn, + chat_id="chat_bot_a", + speaker_bot_id="bot_a", + recent_dialogue=[], + retrieved_memory_summaries=[], + budget_soft=5, + budget_hard=10, + ) diff --git a/tests/test_regenerate.py b/tests/test_regenerate.py new file mode 100644 index 0000000..b561d5f --- /dev/null +++ b/tests/test_regenerate.py @@ -0,0 +1,273 @@ +"""Regenerate flow (T29). + +POST ``/chats//turns//regenerate`` re-streams the +assistant turn, supersedes the prior ``assistant_turn`` event, and — when +prose is supplied — captures a ``user_turn_edit`` event that supersedes +the original ``user_turn``. + +These tests cover the functional core required by the plan: + +- Without edit: a new ``assistant_turn`` is appended; the original is + marked ``superseded_by`` the new one. +- With edit: a ``user_turn_edit`` event is appended; the original + ``user_turn`` is also marked ``superseded_by``. +- Missing event id returns 404. +""" + +from __future__ import annotations + +import json + +import pytest +from fastapi.testclient import TestClient + +from chat.app import app +from chat.db.connection import open_db +from chat.eventlog.log import append_event +from chat.eventlog.projector import project +from chat.llm.mock import MockLLMClient + + +@pytest.fixture +def client(tmp_path, monkeypatch): + cfg = tmp_path / "config.toml" + cfg.write_text('featherless_api_key = "test"\n') + monkeypatch.setenv("CHAT_CONFIG_PATH", str(cfg)) + db = tmp_path / "test.db" + monkeypatch.setenv("CHAT_DB_PATH", str(db)) + with TestClient(app) as c: + # Disable lifespan-managed background worker (would otherwise try + # to score significance through Featherless with the test key). + if hasattr(app.state, "background_worker"): + app.state.background_worker.enabled = False + yield c + app.dependency_overrides.clear() + + +def _seed_with_one_turn(db_path): + """Seed bot, chat, edges/activity, and ONE round of user_turn + assistant_turn. + + Returns ``(user_turn_event_id, assistant_turn_event_id)``. + """ + with open_db(db_path) as conn: + append_event( + conn, + kind="bot_authored", + payload={ + "id": "bot_a", + "name": "BotA", + "persona": "thoughtful", + "voice_samples": [], + "traits": [], + "backstory": "", + "initial_relationship_to_you": "", + "kickoff_prose": "", + }, + ) + append_event( + conn, + kind="chat_created", + payload={ + "id": "chat_bot_a", + "host_bot_id": "bot_a", + "initial_time": "2026-04-26T20:00:00+00:00", + "narrative_anchor": "Day 1", + "weather": "", + }, + ) + append_event( + conn, + kind="edge_update", + payload={ + "source_id": "bot_a", + "target_id": "you", + "chat_id": "chat_bot_a", + }, + ) + append_event( + conn, + kind="edge_update", + payload={ + "source_id": "you", + "target_id": "bot_a", + "chat_id": "chat_bot_a", + }, + ) + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": "you", + "posture": "sitting", + "action": {"verb": "talking"}, + "attention": "", + "holding": [], + "status": {}, + }, + ) + append_event( + conn, + kind="activity_change", + payload={ + "entity_id": "bot_a", + "posture": "sitting", + "action": {"verb": "listening"}, + "attention": "", + "holding": [], + "status": {}, + }, + ) + # First round: user_turn + assistant_turn. + ut_id = append_event( + conn, + kind="user_turn", + payload={ + "chat_id": "chat_bot_a", + "prose": "hello", + "segments": [], + }, + ) + at_id = append_event( + conn, + kind="assistant_turn", + payload={ + "chat_id": "chat_bot_a", + "speaker_id": "bot_a", + "text": "Original response.", + "truncated": False, + "user_turn_id": ut_id, + }, + ) + project(conn) + return ut_id, at_id + + +def test_regenerate_without_edit_creates_new_assistant_turn(client, tmp_path): + """Reissuing the regenerate POST with no prose should: + + - Stream a new ``assistant_turn`` carrying ``regenerated_from`` and + the canned narrative text. + - Mark the original ``assistant_turn`` row as ``superseded_by`` the + new one. + """ + ut_id, at_id = _seed_with_one_turn(tmp_path / "test.db") + + narrative_canned = "New response." + state_canned = json.dumps( + {"affinity_delta": 0, "trust_delta": 0, "knowledge_facts": []} + ) + canned = [narrative_canned, state_canned, state_canned] + + from chat.web.kickoff import get_llm_client + + app.dependency_overrides[get_llm_client] = lambda: MockLLMClient( + canned=list(canned) + ) + try: + response = client.post( + f"/chats/chat_bot_a/turns/{at_id}/regenerate", data={} + ) + assert response.status_code == 204 + finally: + app.dependency_overrides.clear() + + with open_db(tmp_path / "test.db") as conn: + # Original assistant_turn is now superseded. + row = conn.execute( + "SELECT superseded_by FROM event_log WHERE id = ?", (at_id,) + ).fetchone() + assert row[0] is not None + + # A new assistant_turn exists, links back to the original, and + # carries the canned narrative text. + cur = conn.execute( + "SELECT id, payload_json FROM event_log " + "WHERE kind = 'assistant_turn' AND id != ? " + "AND superseded_by IS NULL", + (at_id,), + ).fetchall() + assert len(cur) == 1 + new_id, new_payload_json = cur[0] + new_payload = json.loads(new_payload_json) + assert new_payload["text"] == "New response." + assert new_payload["regenerated_from"] == at_id + # The original assistant_turn's superseded_by points at the new one. + assert row[0] == new_id + + # The original user_turn is NOT touched when no prose was supplied. + ut_row = conn.execute( + "SELECT superseded_by FROM event_log WHERE id = ?", (ut_id,) + ).fetchone() + assert ut_row[0] is None + + +def test_regenerate_with_edit_appends_user_turn_edit(client, tmp_path): + """Supplying ``prose`` should: + + - Append a ``user_turn_edit`` event whose payload references the + original user_turn id and carries the edited prose. + - Mark the original ``user_turn`` as ``superseded_by`` the edit. + """ + ut_id, at_id = _seed_with_one_turn(tmp_path / "test.db") + + narrative_canned = "Reply to edited." + state_canned = json.dumps( + {"affinity_delta": 0, "trust_delta": 0, "knowledge_facts": []} + ) + canned = [narrative_canned, state_canned, state_canned] + + from chat.web.kickoff import get_llm_client + + app.dependency_overrides[get_llm_client] = lambda: MockLLMClient( + canned=list(canned) + ) + try: + response = client.post( + f"/chats/chat_bot_a/turns/{at_id}/regenerate", + data={"prose": "edited prose"}, + ) + assert response.status_code == 204 + finally: + app.dependency_overrides.clear() + + with open_db(tmp_path / "test.db") as conn: + # A user_turn_edit event was appended with the edited prose and + # a back-pointer to the original user_turn. + cur = conn.execute( + "SELECT payload_json FROM event_log WHERE kind = 'user_turn_edit'" + ).fetchall() + assert len(cur) == 1 + edit_payload = json.loads(cur[0][0]) + assert edit_payload["prose"] == "edited prose" + assert edit_payload["supersedes_user_turn_id"] == ut_id + assert edit_payload["chat_id"] == "chat_bot_a" + + # Original user_turn is now superseded. + ut_row = conn.execute( + "SELECT superseded_by FROM event_log WHERE id = ?", (ut_id,) + ).fetchone() + assert ut_row[0] is not None + + # Original assistant_turn is also superseded by the new one. + at_row = conn.execute( + "SELECT superseded_by FROM event_log WHERE id = ?", (at_id,) + ).fetchone() + assert at_row[0] is not None + + +def test_regenerate_404_when_assistant_turn_missing(client, tmp_path): + """An unknown ``event_id`` returns 404.""" + _seed_with_one_turn(tmp_path / "test.db") + + from chat.web.kickoff import get_llm_client + + app.dependency_overrides[get_llm_client] = lambda: MockLLMClient( + canned=["x", "y", "z"] + ) + try: + response = client.post( + "/chats/chat_bot_a/turns/99999/regenerate", data={} + ) + assert response.status_code == 404 + finally: + app.dependency_overrides.clear() diff --git a/tests/test_render.py b/tests/test_render.py new file mode 100644 index 0000000..23c263b --- /dev/null +++ b/tests/test_render.py @@ -0,0 +1,87 @@ +"""Tests for the transcript renderer (Task 33). + +Lightweight markdown for transcript turns: +- ``*action*`` → ``action`` +- ``**bold**`` → ``bold`` +- ``((ooc))`` → ``((ooc))`` +- ``> line`` → ``
    line
    `` +- paragraph breaks (double newline) → ``

    `` +- everything HTML-escaped first + +No headings, no code blocks, no links — out of scope per Requirements §16.3. +""" + +from __future__ import annotations + +from chat.web.render import render_prose, render_turn_html + + +def test_render_prose_escapes_html(): + """Raw HTML in user content must be escaped — no XSS surface.""" + out = render_prose("") + assert "