FabledScribe/src/scribe/mcp/tools/snippets.py

"""Snippet MCP tools: record reusable functions/components for later recall.

A snippet is a Note with note_type='snippet' (see services/snippets.py). Because
snippets are ordinary embedded notes, once recorded they surface through the same
semantic search + title-first auto-inject as everything else — so a reusable
thing recorded once can be recalled before it's re-written as a one-off.

The tools wrap services/snippets.py, mirroring the note/process tools (dedup gate
on create, System association passthrough).
"""
from __future__ import annotations

from scribe.mcp._context import current_user_id
from scribe.mcp.tools import systems as systems_tools
from scribe.services import access as access_svc
from scribe.services import dedup as dedup_svc
from scribe.services import snippets as snippets_svc
from scribe.services.note_usage import attach_usage, record_pulled
from scribe.services import systems as systems_svc


async def list_snippets(
    q: str = "", tag: str = "", limit: int = 50, offset: int = 0,
    project_id: int = 0,
    repo: str = "", path: str = "", symbol: str = "", verification: str = "",
) -> dict:
    """List recorded snippets — the project's pattern library.

    Search here BEFORE building any shape (a component, control, route
    handler, service class, helper, scaffold): a recorded shape is the
    starting point for every later instance, and building without checking is
    how the same button ends up defined four diverging ways.

    Two ways to ask, usable together: by MEANING (`q` — "what do I need this code
    to do?") and by PLACE (`repo`/`path`/`symbol` — "what canonical helpers
    already live in the file I'm about to edit?"). Reach for the place form
    before you write or change code in a file: it is the cheap way to find prior
    art you'd otherwise duplicate a few lines down.

    Args:
        q: Free-text search across name + body (optional). Matches on meaning as
            well as wording, so describe what you need the code to DO.
        tag: Filter to a single tag, e.g. a language like "python" (optional).
        limit: Max results (1-100).
        offset: Skip this many before returning — page through a corpus
            larger than one call. `total` is the unpaged count, so
            offset+limit against it says whether more remains.
        project_id: Narrow to one project. 0 (default) searches every project —
            usually what you want, since a helper you need here may well have
            been written somewhere else.
        repo: Narrow to snippets recorded in this repo, matched exactly — the
            same repo string used when recording, e.g. "Scribe".
        path: Narrow to snippets recorded at this path. Matches the exact file
            OR anything beneath it, so "frontend/src" finds
            "frontend/src/lib/x.ts" as well as itself.
        symbol: Narrow to snippets recorded under this symbol name, exactly.
        verification: Narrow on the drift check (see verify_snippet).
            "attention" is the one to reach for — everything whose recorded
            location or code no longer checks out, plus everything whose verdict
            expired because the snippet was edited after it was checked. Also
            accepts "ok", "unverified", "drifted", or a specific failure:
            "missing", "moved", "changed".

    `repo`/`path`/`symbol` must all match the SAME recorded location, so a
    snippet that lives in repo A and, separately, at path B in another repo is
    not returned for repo=A + path=B.

    Returns {"snippets": [{id, title, tags, preview, usage}], "total": int}. The
    title reads "name — when to reach for it"; open one in full with
    get_snippet(id).

    `usage` is {surfaced_count, pull_count, last_surfaced_at, last_pulled_at}:
    how often the entry has been put in front of an agent versus actually
    opened. Treat a high surfaced_count with a zero pull_count as a prompt to
    fix the record — usually its "when to reach for it" doesn't say when — or to
    delete it. Such an entry is not harmless: it takes a slot in every future
    auto-inject menu and crowds out something useful.

    An entry marked `shared: true` with an `owner` belongs to someone else — one
    person's suggestion, not settled practice here. Weigh it on its merits and
    attribute it when you use it. Searching (passing `q`) also reaches snippets
    shared directly with the operator; browsing without a query deliberately
    does not, so those stay out of ambient results until asked for.
    """
    uid = current_user_id()
    items, total = await snippets_svc.list_snippets(
        uid, q=q or None, tag=tag, limit=max(1, min(limit, 100)),
        offset=max(0, offset),
        project_id=project_id or None,
        repo=repo, path=path, symbol=symbol, verification=verification,
    )
    labeled = await access_svc.label_shared_items(uid, items)
    await attach_usage(labeled)
    return {"snippets": labeled, "total": total}


async def create_snippet(
    name: str,
    code: str,
    language: str = "",
    signature: str = "",
    when_to_use: str = "",
    repo: str = "",
    path: str = "",
    symbol: str = "",
    locations: list[dict] | None = None,
    tags: list[str] | None = None,
    project_id: int = 0,
    system_ids: list[int] | None = None,
    force: bool = False,
    commit_sha: str = "",
) -> dict:
    """Record a shape in the project's pattern library, so every later
    instance starts from it instead of re-deriving it.

    IS THE SHAPE THE POINT, OR THE ADVICE? A snippet is code with a LOCATION —
    that is what lets it surface from the file someone is about to edit. If
    what wants recording is a standing instruction about how to work, it is a
    rule (create_rule); a procedure followed start to finish is a process
    (create_process); what you LEARNED rather than what to copy is a note
    (create_note).

    Reach for this the FIRST time any shape is built — a component, a control,
    a route handler, a service class, a helper, a test scaffold — not only
    when something is judged "reusable": the builder of the first instance
    can't know what will recur, and a missed record is invisible until it
    resurfaces as an uninformed duplicate. Over-recording is safe (dead weight
    shows in the usage counters and can be pruned); under-recording has no
    signal. A deliberate departure from a recorded shape is recorded as its
    own named variant, not left as drift. Before building, search first — the
    shape may already be recorded.

    Args:
        name: Short name of the function/component, e.g. "useDebouncedRef".
        code: The code itself (required).
        language: Language/format, e.g. "python", "vue", "sql". Becomes a tag and
            the code-fence language.
        signature: One-line signature/interface, e.g. "debounce(fn, ms) -> fn".
        when_to_use: One line on when to reach for it — this becomes part of the
            title, so it's what a recall menu shows. Keep it sharp.
        repo/path/symbol: Canonical location of the reference implementation.
        locations: Several locations at once, as [{"repo","path","symbol"}, ...],
            when you already know the thing lives in more than one place. Takes
            precedence over the single repo/path/symbol shorthand.
        tags: Extra plain-string tags (language + "snippet" are added for you).
        project_id: Associate with a project (0 = no project). Snippets surface
            proactively within their project; search finds them across projects.
        system_ids: Ids of the project's Systems to associate this snippet with.
        force: Bypass the near-duplicate gate (see below).
        commit_sha: The commit the code was read at (`git rev-parse HEAD` — you
            have the repo, so it's free). The recorded location is the source
            of truth for the code and the stored body is a cache of it; this
            stamps what the cache is a cache OF, so staleness is judgeable
            later. Optional, but pass it whenever you're recording from a
            checkout.

    Returns the created snippet (including a parsed `snippet` field), OR — when a
    duplicate already exists and force is false — {"duplicate": true,
    "existing_id": ..., "message": ...} and nothing is created. When that happens
    and it really is the same reusable thing found in another place, prefer
    merge_snippets(existing_id, [new...]) — or record then merge — to unify them
    into ONE canonical record (which then carries every call site as a location),
    rather than forcing a second copy with force=true. A tagged record shows
    its `systems`; created untagged in a project, the response carries the
    `systems_hint` question instead — answer it: tag, create the missing
    System, or deliberately skip.

    WHAT THE GATE MATCHES ON. Exact identity first — an existing snippet at the
    same repo · path · symbol, or holding byte-identical code. Those are certain,
    and force is almost never the right answer to them. Only then a semantic
    check, held to a high bar so that VARIANTS of one component are not refused:
    `.btn-primary` and `.btn-secondary` read alike and are two different things,
    so record both (#2518).
    """
    if not (name or "").strip() or not (code or "").strip():
        raise ValueError("create_snippet requires a non-empty name and code")
    uid = current_user_id()

    title = snippets_svc.compose_title(name, when_to_use)
    body = snippets_svc.compose_body(
        code=code, language=language, signature=signature,
        when_to_use=when_to_use, repo=repo, path=path, symbol=symbol,
        locations=locations,
    )
    if not force:
        dup = await dedup_svc.find_duplicate_note(
            uid, title, body, project_id=project_id or None,
            is_task=False, note_type=snippets_svc.SNIPPET_NOTE_TYPE,
            # The artefact itself, not just its description — the gate compares
            # location and code before it compares prose (#2518).
            code=code,
            locations=snippets_svc.resolve_locations(repo, path, symbol, locations),
        )
        if dup is not None:
            return dedup_svc.duplicate_response(dup, "snippet")

    note = await snippets_svc.create_snippet(
        uid, name=name, code=code, language=language, signature=signature,
        when_to_use=when_to_use, repo=repo, path=path, symbol=symbol,
        locations=locations, tags=tags, project_id=project_id or None,
        commit_sha=commit_sha,
    )
    if system_ids:
        await systems_svc.set_record_systems(uid, note.id, system_ids)
    data = snippets_svc.snippet_to_dict(note)
    await systems_tools.attach_systems(uid, uid, data, note.id, project_id or None)
    return data


async def get_snippet(snippet_id: int, project_id: int = 0) -> dict:
    """Fetch a snippet by id — the full record: code, signature, location, and a
    parsed `snippet` field of its structured parts.

    On an instance with a forge configured, the response also carries
    `body_source` + `body_freshness`: "current" means the code was just
    confirmed against the recorded location; "diverged" or "missing" means
    the source moved on — trust the location over the cached body and
    consider verify_snippet after you look.

    A record kept VERBATIM is confirmed by containment. A deliberately
    ANNOTATED one — commentary the source does not carry — cannot be, so it
    reads "current" on the authority of a standing `ok` verdict stamped at
    the very commit just fetched (#2782); `verification` in the same payload
    shows that basis. Edit the record, or let the file move past that commit,
    and it reads "diverged" again until someone re-runs verify_snippet.

    When the shape ledger has judgments against this snippet, the response
    carries `instances` (shapes classified as conforming to it — the
    structured consumer map) and/or `variants` (named departures, each with
    its why). Consult them before changing the snippet's contract: they are
    the call sites your change lands on (classify_shapes maintains them).

    If the record belongs to someone else it carries `shared: true` with the
    `owner` and your `permission`. Read that as ONE PERSON'S SUGGESTION, not as
    established practice here: judge it on its merits, say whose it is when you
    reference it, and don't adopt it as the house pattern without checking.

    `project_id` is the project you are WORKING IN, not this record's own.
    Passing the active project is what makes "opened away from where it was
    written" answerable; 0 leaves it unreported and the pull still counts.
    """
    uid = current_user_id()
    note = await snippets_svc.get_snippet(uid, snippet_id)
    if note is None:
        raise ValueError(f"snippet {snippet_id} not found")
    data = snippets_svc.snippet_to_dict(note)
    # Forge-checked freshness (#2690): attaches body_source/body_freshness
    # when the instance has a forge; a no-forge instance sees no new fields.
    await snippets_svc.attach_live_body(note, data)
    data.update(await access_svc.describe_provenance(uid, note))
    # A "pull" is an explicit open, so it's recorded HERE rather than in
    # snippets_svc.get_snippet — the service is also reached by update/merge
    # paths, and counting those would inflate exactly the number that is
    # supposed to mean "someone chose to look at this" (#2085).
    record_pulled(
        user_id=uid, note_id=int(note.id),
        source="mcp_get_snippet", project_id=project_id,
    )
    await systems_tools.attach_systems(
        uid, note.user_id, data, note.id, note.project_id
    )
    # The structured consumer map (#2789): ledger rows judged against this
    # snippet. Attached only when non-empty (#2483) — and never for projects
    # the caller can't read.
    from scribe.services import shape_ledger as shape_ledger_svc

    consumers = await shape_ledger_svc.snippet_consumers(uid, int(note.id))
    if consumers["instances"]:
        data["instances"] = consumers["instances"]
    if consumers["variants"]:
        data["variants"] = consumers["variants"]
    if consumers.get("uses"):
        # The call sites (#2870): shapes that use this snippet, whatever
        # shape they are themselves.
        data["uses"] = consumers["uses"]
    return data


async def unmerge_snippet(survivor_id: int, source_id: int) -> dict:
    """Reverse ONE source out of a merged snippet — the inverse of merge_snippets.

    Restores the source record and strips exactly what it contributed from the
    survivor: the locations and tags it ADDED at merge time, never the ones the
    survivor already had. Reach for it when a merge turns out to have unified two
    things that only looked alike.

    Also the fix for a half-undone merge. Restoring a merged-in source from the
    trash by hand brings the record back but leaves the survivor still claiming
    its call sites, so both records claim the same places and the reverse lookup
    reads the duplicate claims as real. Running this on an already-restored
    source repairs that: it skips the restore and does the subtraction.

    Args:
        survivor_id: The snippet that absorbed the other.
        source_id: The snippet to pull back out of it.

    Returns {"survivor": {...}, "restored": {...}}.

    Refuses, with the reason, when: the survivor has no record of absorbing that
    id; the source was purged from the trash; or the merge predates per-source
    provenance, in which case what it contributed isn't known and subtracting a
    guess could strip call sites the survivor genuinely owns — restore it from
    the trash and adjust both records by hand instead.
    """
    uid = current_user_id()
    try:
        result = await snippets_svc.unmerge_snippet(uid, survivor_id, source_id)
    except snippets_svc.UnmergeError as exc:
        raise ValueError(str(exc)) from exc
    if result is None:
        raise ValueError(f"snippet {survivor_id} not found")
    survivor, restored = result
    return {
        "survivor": snippets_svc.snippet_to_dict(survivor),
        "restored": snippets_svc.snippet_to_dict(restored) if restored else None,
    }


async def find_duplicate_snippets(threshold: float = 0.0) -> dict:
    """Find snippets already recorded that look like duplicates of each other.

    The create gate PREVENTS a new duplicate and merge_snippets CURES one you
    point it at — this is the missing third piece: it FINDS the ones already in
    the record, so nobody has to notice them by hand.

    Results are grouped into candidate merge SETS, not just pairs. Grouping is
    transitive: if A resembles B and B resembles C, all three land in one set
    even when A and C don't directly clear the bar. That mirrors what merge does
    (it folds every source into one survivor), but it means a chain of mild
    resemblances can rope in a member that isn't really alike — so read a set as
    a proposal and check the members before acting.

    Reports only YOUR snippets. merge_snippets requires one owner across the
    whole set, so surfacing someone else's would propose a merge that can't be
    performed.

    Acting on a group: pick the best record as the canonical target, then
    `merge_snippets(target_id, [other ids])`. Merge unions the fields and folds
    every source's location in, so the survivor is findable at all their call
    sites; the sources are trashed, recoverably. Prefer as target the one with
    the clearest "when to reach for it" — merge keeps the target's title.

    Args:
        threshold: Similarity floor, 0-1. 0 (default) uses the configured
            setting. Raise it if the report is noisy, lower it to catch more.

    Returns {"groups": [{"note_ids", "snippets", "top_score"}], "pairs",
    "threshold"}. An empty `groups` means nothing resembles anything else that
    closely — the common and desirable case.
    """
    uid = current_user_id()
    return await dedup_svc.find_duplicate_snippets(
        uid, threshold=threshold if threshold > 0 else None
    )


async def verify_snippet(
    snippet_id: int, status: str, detail: str = "", path: str = "",
    commit_sha: str = "",
) -> dict:
    """Record whether a snippet's recorded location and code still match source.

    YOU do the checking — Scribe has no copy of the repo and deliberately never
    gets one. This tool only remembers your verdict so it becomes queryable and
    so the operator can see what has rotted.

    The procedure, once per snippet you're checking:
      1. `get_snippet(id)` — read its `snippet.locations` and `snippet.code`.
      2. Does the recorded path still exist in the working tree? If not →
         status="missing".
      3. Does the recorded symbol still appear in that file? If not →
         status="moved" (the file is there, the thing isn't).
      4. Does the source still match the recorded code, allowing for formatting?
         Judge whether it still does the same thing — an added parameter or a
         changed branch is "changed"; a reindent is not. If it diverged →
         status="changed".
      5. All three hold → status="ok".

    Put what you actually found in `detail` ("renamed to parse_location_str",
    "moved to services/knowledge.py"). It's what makes the record fixable later
    by someone who wasn't here, so write it for them, not as a status echo.

    CONSUMERS you enumerate while checking ("all N call sites still route
    through it") are ledger rows, not detail prose: classify each consuming
    definition as an `instance` of this snippet with classify_shapes — prose
    cannot be sorted, queried, or diffed (note 2786's lesson), and the rows
    are what make "what uses this?" answerable forever. `detail` keeps the
    WHY and what changed, nothing that belongs in a row.

    A verdict expires automatically if the snippet is edited afterwards: it is
    stamped with a hash of the code it was checked against, so it can never go
    on vouching for code nobody checked. Re-verify after fixing a record.

    Args:
        snippet_id: The snippet you checked.
        status: "ok" | "missing" | "moved" | "changed".
        detail: What you found — free text, shown to the operator.
        path: The path you actually checked, if it differs from the recorded
            one (e.g. you found the symbol at its new home). Defaults to the
            recorded path.
        commit_sha: The commit the working tree was at when you checked
            (`git rev-parse HEAD`). An "ok" verdict with it also refreshes the
            body's provenance — you just proved the cached code matches the
            source at that commit.

    Requires write access: a verdict changes how the record is presented, so
    being able to read a snippet someone shared with you doesn't let you mark
    it broken.
    """
    uid = current_user_id()
    note = await snippets_svc.record_verification(
        uid, snippet_id, status=status, detail=detail, path=path,
        commit_sha=commit_sha,
    )
    if note is None:
        raise ValueError(
            f"snippet {snippet_id} not found, or you don't have write access to it"
        )
    return snippets_svc.snippet_to_dict(note)


async def update_snippet(
    snippet_id: int,
    name: str | None = None,
    code: str | None = None,
    language: str | None = None,
    signature: str | None = None,
    when_to_use: str | None = None,
    repo: str | None = None,
    path: str | None = None,
    symbol: str | None = None,
    locations: list[dict] | None = None,
    tags: list[str] | None = None,
    project_id: int = 0,
    system_ids: list[int] | None = None,
    commit_sha: str = "",
) -> dict:
    """Update a snippet. Only the fields you pass change.

    An omitted field is left alone; an EMPTY STRING clears it — so a stale
    signature, a wrong "when to use", or an obsolete location can be removed, not
    just overwritten. A snippet that surfaces in recall with wrong details is
    worse than none, so correcting downward has to be possible.

    Args:
        locations: Replace the whole location set, as [{"repo","path","symbol"},
            ...]. Pass [] to clear every location. The single repo/path/symbol
            args instead overlay onto the FIRST location, leaving the rest.
        tags: Replaces the extra-tag set (language + "snippet" are re-derived).
        project_id: 0 leaves it unchanged, -1 detaches it from its project, a
            positive id moves it.
        commit_sha: When you're updating the code from a checkout, the commit
            it was read at (`git rev-parse HEAD`). Restamps the body's
            provenance; changing the code WITHOUT it drops the old stamp,
            since the new body no longer comes from that commit.

    Editing someone else's snippet requires an editor or admin share from them.
    A read-only share is refused with a message saying so — record your own
    version instead of trying to force it.
    """
    uid = current_user_id()
    if project_id == 0:
        project = snippets_svc.UNSET
    elif project_id < 0:
        project = None
    else:
        project = project_id

    try:
        note = await snippets_svc.update_snippet(
            uid, snippet_id,
            name=name, code=code, language=language,
            signature=signature, when_to_use=when_to_use,
            repo=repo, path=path, symbol=symbol,
            locations=locations, tags=tags, project_id=project,
            commit_sha=commit_sha or None,
        )
    except PermissionError as exc:
        # Readable but not writable — surface the real reason, not "not found".
        raise ValueError(str(exc)) from exc
    if note is None:
        raise ValueError(f"snippet {snippet_id} not found")
    if system_ids is not None:
        # The CALLER, not the owner (#4249). `update_snippet` above already
        # raised PermissionError if this user may not write, so the tagging
        # runs with the actor's own System visibility rather than the owner's.
        await systems_svc.set_record_systems(uid, snippet_id, system_ids)
    data = snippets_svc.snippet_to_dict(note)
    data.update(await access_svc.describe_provenance(uid, note))
    await systems_tools.attach_systems(
        uid, note.user_id, data, snippet_id, note.project_id
    )
    return data


async def delete_snippet(snippet_id: int) -> dict:
    """Retire a snippet you recorded — it moves to the trash and is recoverable.

    Reach for this when a snippet is wrong, obsolete, or was never worth keeping.
    A recorded snippet is offered as prior art on every matching turn, so a bad
    one costs more than a missing one. If instead it's a duplicate of something
    that should survive, prefer merge_snippets — that keeps the call sites.
    """
    uid = current_user_id()
    # Read before deleting so the confirmation can NAME what went — an id
    # alone leaves the operator unable to tell which snippet this was.
    # Fail-open: the title is a COURTESY on top of the delete, so a lookup
    # that errors must not stop the delete happening. Same posture the
    # staleness marker takes — a decoration may never break its payload.
    try:
        doomed = await snippets_svc.get_snippet(uid, snippet_id)
        title = getattr(doomed, "title", "") if doomed else ""
    except Exception:
        title = ""
    if not await snippets_svc.delete_snippet(uid, snippet_id):
        raise ValueError(f"snippet {snippet_id} not found")
    return {"deleted": True, "id": snippet_id, "title": title}


async def merge_snippets(target_id: int, source_ids: list[int]) -> dict:
    """Unify duplicate/variant snippets INTO one canonical record — the cure for
    the same reusable thing recorded as several one-offs.

    Keeps the target as the canonical: its name, when-to-use, signature, language
    and code win. The sources' locations and extra tags are folded in — so the
    survivor ends up carrying EVERY call site as a location (which is itself the
    "this is duplicated N times" signal) — and the source records are moved to the
    trash (recoverable). The survivor is re-embedded so recall stops surfacing the
    now-merged duplicates.

    The survivor records what it absorbed as `merged_from` (in its `snippet`
    fields and as a "Merged from: #ids" line in the body), so a variant that got
    folded in leaves a trace outside the trash. It accumulates across merges.

    Reversible: each entry also records what that source contributed, so
    `unmerge_snippet(target_id, source_id)` can restore it and strip exactly
    those locations back off — never the ones the target already had.

    Args:
        target_id: The snippet to keep (the canonical record).
        source_ids: Snippet ids to fold into the target and retire. Ids that
            aren't your snippets are skipped; target_id in the list is ignored.

    Returns the merged canonical snippet (with a parsed `snippet` field) plus
    `merged_ids` — the source ids actually merged and trashed.
    """
    uid = current_user_id()
    ids = [s for s in (source_ids or []) if s != target_id]
    if not ids:
        raise ValueError("merge_snippets requires at least one other source_id")
    try:
        result = await snippets_svc.merge_snippets(uid, target_id, ids)
    except PermissionError as exc:
        raise ValueError(str(exc)) from exc
    if result is None:
        raise ValueError(f"snippet {target_id} not found")
    note, merged_ids = result
    data = snippets_svc.snippet_to_dict(note)
    data["merged_ids"] = merged_ids
    return data


def register(mcp) -> None:
    for fn in (
        list_snippets, create_snippet, get_snippet, update_snippet,
        delete_snippet, merge_snippets, verify_snippet, find_duplicate_snippets,
        unmerge_snippet,
    ):
        mcp.tool(name=fn.__name__)(fn)