interactive-story/backend/app/schemas.py

from datetime import datetime
from typing import Annotated, Literal

from pydantic import BaseModel, ConfigDict, Field, computed_field

from . import images

# Length caps (Phase 9). The VARCHAR caps are a correctness requirement rather
# than only an abuse limit. Postgres enforces column lengths and SQLite never
# did, so a longer value has to be a 422 here rather than a 500 at INSERT. The
# text-column caps are generous abuse ceilings that a legitimate player does not
# reach.
NAME_MAX = 200          # Titles and names. VARCHAR(200).
TAGS_MAX = 500          # VARCHAR(500).
CARD_TYPE_MAX = 100     # VARCHAR(100).
PROSE_MAX = 50_000      # Memory, author's note, prompts, entries, and notes.
ACTION_MAX = 20_000     # One player action.
MEMORY_TEXT_MAX = 5_000
# A scenario cover image, stored inline as a base64 data URI. A 400x300 WebP at
# the quality the editor encodes runs about 20 to 40 kB. A cap of 400 kB leaves
# room for a client that downscales less aggressively, and it stops anyone from
# storing a multi-megabyte PNG in a row that every list request reads.
IMAGE_MAX = 400_000
ICON_MAX = 16           # One emoji or glyph. VARCHAR(16).
BRANCH_NAME_MAX = 80    # What a player called one line of the story. VARCHAR(80).
PERSONA_NAME_MAX = 80   # The protagonist's name. VARCHAR(80).
PERSONA_PRONOUNS_MAX = 40   # "they/them" and the like. VARCHAR(40).
# M4: what a player called a Save Point. VARCHAR(120). Wider than a branch name
# because these are sentences rather than labels — "Before entering the abbey"
# is the example the specification uses throughout.
CHECKPOINT_NAME_MAX = 120

Name = Annotated[str, Field(max_length=NAME_MAX)]
Tags = Annotated[str, Field(max_length=TAGS_MAX)]
CardType = Annotated[str, Field(max_length=CARD_TYPE_MAX)]
Prose = Annotated[str, Field(max_length=PROSE_MAX)]
ActionText = Annotated[str, Field(max_length=ACTION_MAX)]
Image = Annotated[str, Field(max_length=IMAGE_MAX)]
Icon = Annotated[str, Field(max_length=ICON_MAX)]
PersonaName = Annotated[str, Field(max_length=PERSONA_NAME_MAX)]
PersonaPronouns = Annotated[str, Field(max_length=PERSONA_PRONOUNS_MAX)]
CheckpointName = Annotated[str, Field(max_length=CHECKPOINT_NAME_MAX)]


class ORMModel(BaseModel):
    model_config = ConfigDict(from_attributes=True)


# ---------- Story cards ----------

class StoryCardBase(BaseModel):
    type: CardType = ""
    name: Name = ""
    keys: Prose = ""
    entry: Prose = ""
    notes: Prose = ""


class StoryCardCreate(StoryCardBase):
    scenario_id: int | None = None
    adventure_id: int | None = None


class StoryCardUpdate(BaseModel):
    type: CardType | None = None
    name: Name | None = None
    keys: Prose | None = None
    entry: Prose | None = None
    notes: Prose | None = None


class StoryCardOut(ORMModel, StoryCardBase):
    id: int
    scenario_id: int | None
    adventure_id: int | None


# ---------- Scenarios ----------

class ScenarioBase(BaseModel):
    title: Name = "Untitled Scenario"
    description: Prose = ""
    prompt: Prose = ""
    memory: Prose = ""
    authors_note: Prose = ""
    ai_instructions: Prose = ""
    tags: Tags = ""
    # Cover art, either an https URL or a base64 data URI. See `app/images.py`.
    image: Image = ""
    # The emoji or glyph shown when `image` is empty.
    icon: Icon = ""
    # Phase 12: the RPG world-state template, holding stat definitions, bands,
    # rules, and milestones. `None` means the scenario has no RPG layer.
    stat_schema: dict | None = None


class ScenarioCreate(ScenarioBase):
    pass


class ScenarioUpdate(BaseModel):
    title: Name | None = None
    description: Prose | None = None
    prompt: Prose | None = None
    memory: Prose | None = None
    authors_note: Prose | None = None
    ai_instructions: Prose | None = None
    tags: Tags | None = None
    image: Image | None = None
    icon: Icon | None = None
    stat_schema: dict | None = None


class ScenarioOut(ORMModel, ScenarioBase):
    id: int
    is_public: bool = False  # Shared demo content, read-only for everyone.
    created_at: datetime
    updated_at: datetime
    story_cards: list[StoryCardOut] = []


class ScenarioListItem(ORMModel):
    id: int
    title: str
    description: str
    tags: str
    is_public: bool = False
    updated_at: datetime
    # Read from the row so that `image_url` can be derived, and excluded from
    # the response, because a list of base64 data URIs would be megabytes of
    # JSON.
    image: str = Field("", exclude=True)
    icon: str = ""

    @computed_field
    @property
    def image_url(self) -> str:
        return images.public_url(self.id, self.image, self.updated_at)


# ---------- Adventures ----------

class AdventureCreate(BaseModel):
    scenario_id: int | None = None
    title: Name | None = None
    # M8: the opening scene, for a campaign started without a scenario.
    #
    # A scenario's `prompt` already becomes the campaign's `start` action, and
    # this is the same thing said directly. It exists because M8's setup flow
    # creates a campaign from a form rather than from a template
    # (`BROWSER-UX-SPEC.md` §41), and without it every new campaign opens on a
    # blank page — the reader has to invent the situation *and* the first move
    # in one box. Ignored when `scenario_id` is given, which already supplies one.
    opening: Prose = ""
    # M8: the campaign's own rules, as a list of sentences.
    #
    # The column has existed since migration 82 and both the prompt
    # (`context/builder._canon_section`) and the state validator
    # (`narrative/apply`) already read it — it simply had no way in from the
    # browser, so a fixture had to write it with SQL. This is the highest
    # authority in the campaign, which is exactly why a person setting one up
    # needs to be able to state it.
    canon_rules: list[Name] = []
    # The `${Placeholder}` values collected from the player at the start, which
    # is the AI Dungeon behavior.
    placeholders: dict[str, str] = {}
    # Phase 18: who the player is playing as, collected by the same modal. These
    # are independent of `placeholders`: a scenario that asks for `${Name}` is
    # asking its own question, and nothing here fills it in.
    persona_name: PersonaName = ""
    persona_pronouns: PersonaPronouns = ""
    persona_desc: Prose = ""


class AdventureUpdate(BaseModel):
    title: Name | None = None
    memory: Prose | None = None
    authors_note: Prose | None = None
    ai_instructions: Prose | None = None
    story_summary: Prose | None = None
    auto_summarize: bool | None = None
    memory_bank_enabled: bool | None = None
    persona_name: PersonaName | None = None
    persona_pronouns: PersonaPronouns | None = None
    persona_desc: Prose | None = None
    # M8. See `AdventureCreate.canon_rules`. Editable after setup because canon
    # is the thing a reader most often gets wrong first and needs to correct —
    # "resurrection is impossible" is easier to write once the story has tried it.
    canon_rules: list[Name] | None = None


class AdventureRefresh(BaseModel):
    """The body for "Update from scenario".

    `placeholders` supplies answers the adventure has no stored value for. See
    `AdventureCreate.placeholders`. The answers are merged over the stored ones
    and saved.
    """

    placeholders: dict[str, str] = {}


class RefreshPlan(BaseModel):
    """What a refresh would change. The confirm dialog is built from this."""

    scenario_id: int
    scenario_title: str
    has_changes: bool
    # Maps a field name to `{"old": ..., "new": ...}`, for differing fields
    # only.
    fields: dict[str, dict] = {}
    # Maps "added", "updated", or "removed" to a list of card names.
    cards: dict[str, list[str]] = {}
    # Maps "added" or "removed" to a list of stat paths. Live values are
    # otherwise kept.
    world_state: dict[str, list[str]] = {}
    # The `${Placeholder}` names the scenario asks for that the adventure has
    # no stored answer to. The client collects these and sends them back.
    placeholders_needed: list[str] = []


class ActionOut(ORMModel):
    id: int
    adventure_id: int
    type: str
    text: str
    reasoning: str | None = None
    # Phase 12: the compact RPG state changes for this turn, read from the
    # model property. Legacy as of M5 and empty on new turns; kept so a pre-M5
    # campaign's chips still render.
    world_changes: list[dict] = []
    # M5: what this turn changed, as short lines for the chip under an AI
    # message. Read from `Action.state_summary`, which reads the small
    # bulk-loaded column rather than the deferred snapshot.
    state_summary: list[str] = []
    # SP9: the pager, such as `2/4`. It reports how many attempts this turn has
    # and which one is on screen. It is keyed on the parent, so it counts the
    # attempts of this turn rather than every node that shares a depth, and it
    # keeps counting them after one has been forked onto its own branch.
    #
    # A turn nobody has retaken reads 1/1, which is most turns, and the client
    # draws no pager for a count of one. The attempts themselves come from
    # `GET /actions/{id}/variants`, so this payload stays small.
    take_count: int = 1
    take_index: int = 0
    # Which line this node is on, so the pager can distinguish the two kinds of
    # step without asking the server. An attempt on this branch is a leaf with
    # nothing below it, so showing it is a local change. An attempt on another
    # branch has a story of its own, so moving to it is a branch switch.
    branch_id: int | None = None
    created_at: datetime


class VariantOut(BaseModel):
    # Since SP4 every attempt is its own node, so each one has an id, and the
    # client needs that id. A fork is addressed by the attempt being promoted,
    # not by its position in a group that renumbers whenever an attempt is
    # added.
    id: int
    index: int
    text: str
    reasoning: str | None = None
    # See `ActionOut.branch_id`. It decides whether choosing this attempt is a
    # local step or a branch switch.
    branch_id: int | None = None
    created_at: str | None = None
    active: bool = False


class VariantSelect(BaseModel):
    index: int = Field(ge=0)


class BranchOut(ORMModel):
    """One line through the story tree (Phase 14, SP5).

    This carries enough to draw the tree and nothing more. `fork_depth` is where
    this line leaves its parent, and `depth` is where it currently ends, so a
    fork is two numbers rather than a walk. `own_actions` counts the turns played
    on this branch itself. The rest of its story is borrowed from its ancestors,
    which is why the number is smaller than a reader expects.
    """

    id: int
    parent_branch_id: int | None = None
    fork_depth: int | None = None
    depth: int
    own_actions: int = 0
    # M4: how many Save Points name a position on this line. Deleting the branch
    # deletes them with its story, so the panel warns with a number rather than
    # a vague caution. Zero for a line nobody has bookmarked, which is most.
    save_points: int = 0
    is_head: bool = False
    # NULL for a branch nobody has named. The client labels those from the fork
    # depth rather than the server inventing a name. See the column comment.
    name: str | None = None
    created_at: datetime


class BranchRename(BaseModel):
    """A name a player chose, or `null` to make the branch unnamed again."""

    name: Annotated[str, Field(max_length=BRANCH_NAME_MAX)] | None = None


# ---------- Narrative state (M5) ----------


class StateGroup(BaseModel):
    """One labelled section of the state inspector.

    Rows carry the key as well as the label, because a manual correction has to
    name an entity and the user should not have to guess the identifier.
    """

    title: str
    rows: list[dict] = []


class NarrativeStateOut(BaseModel):
    """The authoritative state at the active head.

    `groups` is the display form and `document` is the state itself. Both are
    returned because they answer different questions: the panel renders the
    first, and a correction form — or a test — needs the second to name a key.
    """

    groups: list[StateGroup] = []
    empty: bool = True
    document: dict = {}


class StateEventIn(BaseModel):
    """One typed event, as a client proposes it.

    Deliberately loose about which fields are present: the event vocabulary is
    defined in `narrative/events.py` and enforced by `narrative/validate.py`,
    and duplicating those rules here would create a second, drifting copy of the
    allowlist. What this model does is bound the shapes — a type that is a
    string, values that are scalars, labels that are short strings — so a
    payload cannot smuggle a structure past Pydantic and reach the validator as
    something other than an event.
    """

    model_config = ConfigDict(extra="allow")

    type: Annotated[str, Field(max_length=60)]


class StateCorrection(BaseModel):
    """A manual correction: the user overruling what the story established.

    `note` records why, in the user's words, and is kept on the proposal record
    so the audit says more than "the user changed this".
    """

    events: Annotated[list[StateEventIn], Field(min_length=1, max_length=20)]
    note: Prose = ""


class StateEventOut(ORMModel):
    """One accepted change, for the audit view."""

    id: int
    action_id: int | None = None
    branch_id: int | None = None
    depth: int | None = None
    # The reader-facing position, matching the Save Point panel's vocabulary.
    turn: int | None = None
    sequence: int = 0
    event_type: str
    payload: dict = {}
    before: dict | None = None
    source: str = "accepted_story"
    created_at: datetime


# ---------- Save Points (M4) ----------
#
# "Save Point" is the user-facing term and `checkpoint` is the internal one
# (`BROWSER-UX-SPEC.md` §23). The wire format uses the internal name, as the
# rest of this module does.


class CheckpointOut(ORMModel):
    """One Save Point: a name and the position it names.

    The position is reported three ways because the panel needs three different
    things from it. `turn` is what a reader counts — the same `depth + 1` the
    branch list shows. `depth` and `branch_id` are the coordinate itself.
    `on_path` says whether the position lies on the story being read, which is
    how the panel can tell a Save Point on this line from one naming a line the
    story has left; restoring either works, but they are not the same offer.

    `resolved` is false when the coordinate no longer names a live turn, which
    an action deleted out of the middle of a story can do. Restore refuses such
    a Save Point rather than moving the head somewhere approximate, so the list
    says so before the button is pressed.
    """

    id: int
    adventure_id: int
    name: str
    note: str = ""
    branch_id: int
    depth: int
    turn: int = 0
    on_path: bool = True
    resolved: bool = True
    created_at: datetime
    updated_at: datetime


class CheckpointCreate(BaseModel):
    """A Save Point at wherever the story is being read.

    The position is not a field. A Save Point is made at the campaign's active
    head, which the server already knows, and accepting a coordinate from the
    client would be the second way to name a position — the thing this milestone
    exists not to build.
    """

    name: CheckpointName
    note: Prose = ""


class CheckpointRename(BaseModel):
    """A new label, and nothing else.

    There is deliberately no coordinate here. `STORY-BRANCH-SEMANTICS.md` §24
    keeps a Save Point's meaning auditable by refusing to move one: rename it,
    or delete it and make another where you are.
    """

    name: CheckpointName | None = None
    note: Prose | None = None


class ActionUpdate(BaseModel):
    text: ActionText


class ActionCreate(BaseModel):
    type: Literal["do", "say", "story", "continue"]
    text: ActionText = ""
    # The node this action is played after (SP9). Omitting it means the tip,
    # which is what every ordinary turn uses.
    #
    # Naming an attempt the story moved past is what creates a branch. Stepping
    # between attempts costs nothing and creates nothing, and the fork happens
    # on the first text written below one. That is the first moment the player
    # states which line they mean. Before it, they were reading.
    after_id: int | None = None


class TakeCreate(BaseModel):
    """Another attempt at a turn (SP9).

    `text` is what the player says instead, and it applies only when the turn was
    the player's. An AI turn's other attempt is generated, so the field is
    ignored there rather than rejected. The client makes the same request for
    both, and the node type decides what happens.
    """

    text: ActionText = ""


class AdventureOut(ORMModel):
    id: int
    scenario_id: int | None
    title: str
    memory: str
    authors_note: str
    ai_instructions: str
    story_summary: str
    auto_summarize: bool
    memory_bank_enabled: bool
    persona_name: str
    persona_pronouns: str
    persona_desc: str
    # M8. Read from the `canon_rules` property on the model, which pulls the
    # sentence list out of the stored `campaign_canon` document.
    canon_rules: list[str] = []
    created_at: datetime
    updated_at: datetime
    story_cards: list[StoryCardOut] = []
    # The newest window of the story, not all of it. Older pages arrive from
    # `GET /{id}/actions` as the reader scrolls up. `action_count` is the whole
    # story's length, which is how the client knows more actions exist above.
    actions: list[ActionOut] = []
    action_count: int = 0
    # M3. Whether the history controls have anywhere to go from where the story
    # is. The client cannot work either out for itself: `can_undo` needs the
    # campaign opening, which may be off the top of the loaded window, and
    # `can_redo` needs the retained future, which the client is never sent.
    can_undo: bool = False
    can_redo: bool = False


class ActionPage(BaseModel):
    """A slice of the story, counted back from the newest action."""

    actions: list[ActionOut] = []
    total: int = 0
    # Whether anything older than this slice exists. The server computes it, so
    # the client never has to do arithmetic on positions to find the end.
    has_more: bool = False
    # The same two flags `AdventureOut` carries, so that the response to Undo,
    # Redo or a turn updates the controls without a second request.
    can_undo: bool = False
    can_redo: bool = False


# ---------- Memory bank (Phase 6) ----------

class MemoryOut(ORMModel):
    id: int
    adventure_id: int
    text: str
    pinned: bool
    forgotten: bool
    embedded: bool  # model property: embedding vector present
    use_count: int
    last_used_at: datetime | None
    source_start: int | None
    source_end: int | None
    created_at: datetime


class MemoryCreate(BaseModel):
    text: Annotated[str, Field(max_length=MEMORY_TEXT_MAX)]


class MemoryUpdate(BaseModel):
    text: Annotated[str, Field(max_length=MEMORY_TEXT_MAX)] | None = None
    pinned: bool | None = None
    forgotten: bool | None = None


# ---------------------------------------------------------------- M7: knowledge


class KnowledgeSourceOut(BaseModel):
    """One imported source, as a list row.

    Deliberately without `content`. A library of twenty files would otherwise
    put every byte of every one of them on a screen that shows none of it;
    `KnowledgeSourceDetail` is what serves the text when it is asked for.
    """

    id: int
    title: str
    original_filename: str
    classification: str
    enabled: bool
    visibility: str
    always_include: bool
    content_hash: str
    byte_size: int
    media_type: str
    chunk_count: int
    embedded_count: int
    # The two halves of derived state, kept apart on purpose. Lexical retrieval
    # is a supported production path, so "the vectors failed" and "the index
    # failed" are different sentences with different consequences.
    index_state: str
    index_detail: str
    embed_state: str
    embed_detail: str
    parser_version: int
    chunking_version: int
    imported_at: str | None = None
    updated_at: str | None = None


class KnowledgeSourceDetail(KnowledgeSourceOut):
    """A source with its text, for the inspector.

    `content` is the file as it was decoded, not the normalized form used for
    hashing and search: the reader inspects what they imported
    (`IMPORTED-KNOWLEDGE-DESIGN.md` §61).
    """

    content: str
    notes: str = ""


class KnowledgeChunkOut(BaseModel):
    id: int
    chunk_index: int
    heading_path: str
    text: str
    token_count: int
    content_hash: str
    embedded: bool
    embedding_model: str = ""


class KnowledgeSourceUpdate(BaseModel):
    """What a reader may change about a source without reimporting it.

    Everything here is metadata or state. Nothing rewrites content, and nothing
    is destructive: changing a classification re-frames and re-weights the same
    passages, and disabling a source removes it from retrieval while leaving the
    rows exactly where they are.
    """

    title: str | None = None
    classification: str | None = None
    enabled: bool | None = None
    visibility: str | None = None
    always_include: bool | None = None
    notes: str | None = None


class AdventureListItem(ORMModel):
    id: int
    scenario_id: int | None
    scenario_title: str | None = None
    title: str
    updated_at: datetime
    action_count: int = 0
    # The end of the most recent narration, so a Continue card can show the
    # story rather than only a turn count.
    snippet: str = ""
    # Cover art inherited from the parent scenario. See `app/images.py`.
    image_url: str = ""
    icon: str = ""


# ---------- Auth (Phase 8) ----------

class AuthCredentials(BaseModel):
    email: Annotated[str, Field(max_length=320)]  # VARCHAR(320).
    # The upper bound keeps the scrypt cost constant. Without it, hashing a
    # megabyte password would give an attacker free CPU time.
    password: Annotated[str, Field(max_length=128)]


# ---------- Settings ----------

class SettingsOut(ORMModel):
    endpoint_url: str
    model: str
    api_mode: str
    temperature: float
    max_output_tokens: int
    context_token_budget: int
    model_timeout_seconds: int
    narrator_prompt: str
    summary_model: str
    embedding_model: str
    memory_bank_capacity: int
    memory_top_k: int


ScenarioOut.model_rebuild()


# ---------- AI Chat (power users) ----------
# A scratchpad for talking to a model directly, with no story framing. The
# server persists nothing, so these caps are per-request abuse limits only.

CHAT_MESSAGE_MAX = 100_000   # One message.
CHAT_TOTAL_MAX = 400_000     # The whole conversation sent per request.
CHAT_MESSAGES_MAX = 200      # Turns per request.


class ChatMessage(BaseModel):
    role: Literal["system", "user", "assistant"]
    content: Annotated[str, Field(max_length=CHAT_MESSAGE_MAX)]


class ChatRequest(BaseModel):
    messages: Annotated[list[ChatMessage], Field(min_length=1, max_length=CHAT_MESSAGES_MAX)]
    # If this field is empty or omitted, the user's configured model is used.
    model: Name | None = None
    temperature: Annotated[float, Field(ge=0, le=5)] | None = None
    max_tokens: Annotated[int, Field(ge=1, le=100_000)] | None = None


class SettingsUpdate(BaseModel):
    endpoint_url: Annotated[str, Field(max_length=500)] | None = None  # VARCHAR(500).
    model: Name | None = None
    api_mode: Annotated[str, Field(max_length=20)] | None = None
    temperature: Annotated[float, Field(ge=0, le=5)] | None = None
    max_output_tokens: Annotated[int, Field(ge=1, le=100_000)] | None = None
    context_token_budget: Annotated[int, Field(ge=256, le=200_000)] | None = None
    # Seconds to wait for the model. The floor is high enough that a normal
    # turn cannot trip it; the ceiling exists so that "wait longer" stays a
    # number rather than becoming "wait forever".
    model_timeout_seconds: Annotated[int, Field(ge=30, le=3600)] | None = None
    narrator_prompt: Prose | None = None
    summary_model: Name | None = None
    embedding_model: Name | None = None
    memory_bank_capacity: Annotated[int, Field(ge=1, le=1000)] | None = None
    memory_top_k: Annotated[int, Field(ge=1, le=50)] | None = None