Rules become findable: canon catalog, triggers, tiers, edges, retrieval, surfacing (milestone 307, steps 1–5) #131

Merged
bvandeusen merged 13 commits from dev into main 2026-08-26 17:12:40 -04:00
50 changed files with 3824 additions and 220 deletions
+109
View File
@@ -0,0 +1,109 @@
"""canonical_systems — the global area vocabulary, promoted from a constant
to a table (milestone 307 step 1, decision note 3026)
Revision ID: 0087
Revises: 0086
Create Date: 2026-08-26
The eight standard area names already existed as `STANDARD_SYSTEMS`, a tuple in
services/systems.py that milestone 297 seeds into a project at inception. A
constant cannot be referenced: a rule that applies across projects has nothing
to point at, because `systems.project_id` is NOT NULL and a family rule cannot
be chained to one project's row. This makes the vocabulary a table so it can be
a foreign key, and adds the nullable `systems.canonical_id` that maps a
project's local System onto it.
Deliberately no `user_id`: the catalog is GLOBAL so a shared project inherits
the vocabulary rather than re-earning it. `record_systems` is untouched — it
joins note_id/system_id and never sees this table, so no association data
moves, and no System's own `name` is rewritten.
The seed rows are written here verbatim rather than imported from the service:
a migration is a historical record and must keep running unchanged after the
service's list moves on.
"""
import sqlalchemy as sa
from alembic import op
revision = "0087"
down_revision = "0086"
branch_labels = None
depends_on = None
# (name, slug, description) — the milestone-297 vocabulary, with the slug the
# service computes (canonical_slug: lowercase, "&" -> "and", non-alphanumerics
# collapsed to "-"). Charters stay generic on purpose: a project refines its
# own System's description, never this one. Nothing here names an app, a repo,
# a vendor or a house convention — the catalog ships to every install (rule 115).
_SEED = (
("CI & Release", "ci-and-release",
"How the project is verified and shipped: pipelines, runners, image/artifact builds, release tagging and rollback."),
("Auth & Access", "auth-and-access",
"Who may do what: identity, sessions/tokens, permissions and the scoping of every read and write to the right users."),
("Data Model & Storage", "data-model-and-storage",
"What is stored and how it is shaped: the schema, migrations, serialisation and the services that own a table's lifecycle."),
("API Surface", "api-surface",
"The doors into the capability: HTTP routes, tool/RPC surfaces, request parsing, error envelopes and their contracts."),
("UI & Design", "ui-and-design",
"What people see and touch: views, components, client state, and the design tokens/recipes they are built from."),
("Import & Export", "import-and-export",
"Data crossing the boundary: backups, exports, imports, sync with other systems, file formats."),
("Background Jobs", "background-jobs",
"Work that runs without a request: schedulers, queues, periodic ticks, retention and maintenance."),
("Observability", "observability",
"How the system reports on itself: logging, metrics, audit trails, health and diagnostics."),
)
def upgrade() -> None:
canonical_systems = op.create_table(
"canonical_systems",
sa.Column("id", sa.Integer(), primary_key=True),
sa.Column("name", sa.Text(), nullable=False),
sa.Column("slug", sa.Text(), nullable=False),
sa.Column("description", sa.Text(), nullable=True),
sa.Column("order_index", sa.Integer(), nullable=False, server_default="0"),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
sa.Column("deleted_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("deleted_batch_id", sa.Text(), nullable=True),
)
# Unique among LIVE rows only, so a soft-deleted entry doesn't block
# recreating or restoring the same area (the rules/topics convention).
op.create_index(
"uq_canonical_systems_slug", "canonical_systems", ["slug"],
unique=True, postgresql_where=sa.text("deleted_at IS NULL"),
)
op.bulk_insert(
canonical_systems,
[
{"name": name, "slug": slug, "description": description, "order_index": index}
for index, (name, slug, description) in enumerate(_SEED)
],
)
op.add_column(
"systems",
sa.Column("canonical_id", sa.Integer(), nullable=True),
)
# SET NULL, not CASCADE: retiring a catalog entry must never delete a
# project's System along with it.
op.create_foreign_key(
"fk_systems_canonical_id", "systems", "canonical_systems",
["canonical_id"], ["id"], ondelete="SET NULL",
)
op.create_index("ix_systems_canonical_id", "systems", ["canonical_id"])
# Existing Systems are left UNMAPPED on purpose. An exact-slug match would
# be safe, but a near miss ("CI & runners" vs "CI & Release") is a judgment
# call — those go through the propose/confirm path so a human approves each
# one, rather than being decided by a migration nobody reviews.
def downgrade() -> None:
op.drop_index("ix_systems_canonical_id", table_name="systems")
op.drop_constraint("fk_systems_canonical_id", "systems", type_="foreignkey")
op.drop_column("systems", "canonical_id")
op.drop_index("uq_canonical_systems_slug", table_name="canonical_systems")
op.drop_table("canonical_systems")
@@ -0,0 +1,105 @@
"""rules gain a trigger, a tier, canon tags and typed edges (milestone 307
step 3, decision note 3026)
Revision ID: 0088
Revises: 0087
Create Date: 2026-08-26
A rule could not say WHEN it applies, WHICH area it is about, or WHAT other
rule it belongs with. All three were being written as prose instead — a
project's System description restating rule text, a rule's `why` naming the
note that caused it, and two halves of one shape merged into a single row
because either could surface without the other.
Four additions, each replacing something that was already being said in words:
- `when_to_apply` — the trigger. Nullable HERE and required at the service
layer, because existing rules have none and a migration cannot invent one.
- `tier` — `always_on` (preloaded, as everything is today) or `conditional`
(reachable, surfaced when its trigger fires). Defaults to `always_on`, so
this migration changes NOTHING about which rules bind: an install upgrades
and every rule keeps arriving exactly as it did.
- `arose_from_id` — the record that caused the rule, the edge notes and tasks
already have.
- `rule_systems` / `rule_relations` — the canon tag and the typed edges.
"""
import sqlalchemy as sa
from alembic import op
revision = "0088"
down_revision = "0087"
branch_labels = None
depends_on = None
# Kept in one place so upgrade and the CHECK agree by construction (rule 36:
# a whitelisted value means DROP + ADD CONSTRAINT in the same migration —
# there is no prior constraint here, so the pair is created together).
_TIERS = ("always_on", "conditional")
_RELATION_KINDS = ("co_surfaces", "overrides", "elaborates")
def _in_list(column: str, values: tuple[str, ...]) -> str:
return f"{column} IN (" + ", ".join(f"'{v}'" for v in values) + ")"
def upgrade() -> None:
op.add_column("rules", sa.Column("when_to_apply", sa.Text(), nullable=True))
op.add_column(
"rules",
sa.Column("tier", sa.Text(), nullable=False, server_default="always_on"),
)
op.create_check_constraint("ck_rules_tier", "rules", _in_list("tier", _TIERS))
# SET NULL, not CASCADE: the record that prompted a rule can be trashed
# without taking the rule with it — provenance is a claim about history,
# and losing the source does not repeal the rule.
op.add_column("rules", sa.Column("arose_from_id", sa.BigInteger(), nullable=True))
op.create_foreign_key(
"fk_rules_arose_from_id", "rules", "notes",
["arose_from_id"], ["id"], ondelete="SET NULL",
)
# Which global AREA a rule is about. Points at the canonical catalog, never
# at a project's `systems` row — a rule that spans projects cannot be
# chained to one project's vocabulary (0087).
op.create_table(
"rule_systems",
sa.Column("rule_id", sa.BigInteger(), sa.ForeignKey("rules.id", ondelete="CASCADE"), primary_key=True),
sa.Column("canonical_id", sa.Integer(), sa.ForeignKey("canonical_systems.id", ondelete="CASCADE"), primary_key=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
)
op.create_index("ix_rule_systems_canonical_id", "rule_systems", ["canonical_id"])
# Typed edges between rules. Each kind exists because its absence forced a
# workaround: co_surfaces (merging two rules into one row), overrides (a
# stricter project rule written as a duplicate), elaborates (a local
# addendum sitting beside its parent with nothing to say it is one).
op.create_table(
"rule_relations",
sa.Column("id", sa.BigInteger(), primary_key=True),
sa.Column("from_rule_id", sa.BigInteger(), sa.ForeignKey("rules.id", ondelete="CASCADE"), nullable=False),
sa.Column("to_rule_id", sa.BigInteger(), sa.ForeignKey("rules.id", ondelete="CASCADE"), nullable=False),
sa.Column("kind", sa.Text(), nullable=False),
sa.Column("note", sa.Text(), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
sa.CheckConstraint(_in_list("kind", _RELATION_KINDS), name="ck_rule_relations_kind"),
# A rule cannot relate to itself, and one pair carries a given kind
# once — a second row would surface the same rule twice.
sa.CheckConstraint("from_rule_id <> to_rule_id", name="ck_rule_relations_not_self"),
sa.UniqueConstraint("from_rule_id", "to_rule_id", "kind", name="uq_rule_relations_edge"),
)
op.create_index("ix_rule_relations_from", "rule_relations", ["from_rule_id"])
op.create_index("ix_rule_relations_to", "rule_relations", ["to_rule_id"])
def downgrade() -> None:
op.drop_index("ix_rule_relations_to", table_name="rule_relations")
op.drop_index("ix_rule_relations_from", table_name="rule_relations")
op.drop_table("rule_relations")
op.drop_index("ix_rule_systems_canonical_id", table_name="rule_systems")
op.drop_table("rule_systems")
op.drop_constraint("fk_rules_arose_from_id", "rules", type_="foreignkey")
op.drop_column("rules", "arose_from_id")
op.drop_constraint("ck_rules_tier", "rules", type_="check")
op.drop_column("rules", "tier")
op.drop_column("rules", "when_to_apply")
+58
View File
@@ -0,0 +1,58 @@
"""rule_embeddings — rules become findable by meaning (milestone 307 step 4,
decision note 3026)
Revision ID: 0089
Revises: 0088
Create Date: 2026-08-26
Rules were the only major record type with no vector, so `search` could never
return one and a rule could only ever arrive by being preloaded. That single
fact is what made every rule compete for the same always-on budget.
A sibling table rather than a generalisation of note_embeddings: the row could
have been made polymorphic, but the SEARCH could not — semantic_search_notes is
Note-specific scoping end to end, and a rule shares none of it. See the model
docstring for the full reasoning.
The vectors are DERIVED data. Nothing is backfilled here: the startup backfill
regenerates them, which is also how a chunker-version bump is handled.
"""
import sqlalchemy as sa
from alembic import op
revision = "0089"
down_revision = "0088"
branch_labels = None
depends_on = None
# Matches note_embeddings — bge-small-en-v1.5, 384-dim unit-normalized.
_EMBEDDING_DIM = 384
def upgrade() -> None:
op.create_table(
"rule_embeddings",
sa.Column("rule_id", sa.BigInteger(), sa.ForeignKey("rules.id", ondelete="CASCADE"), primary_key=True),
sa.Column("chunk_index", sa.Integer(), primary_key=True),
sa.Column("chunk_text", sa.Text(), nullable=False),
sa.Column("chunker_version", sa.Integer(), nullable=False),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
)
# The vector column is added by raw DDL for the same reason 0067 did it:
# the type comes from the pgvector extension, not from SQLAlchemy's
# type system.
op.execute(f"ALTER TABLE rule_embeddings ADD COLUMN embedding vector({_EMBEDDING_DIM}) NOT NULL")
# HNSW for cosine distance — matches Vector.cosine_distance (`<=>`), so the
# search is an indexed ORDER BY ... LIMIT k rather than a full scan.
op.execute(
"""
CREATE INDEX ix_rule_embeddings_embedding_hnsw
ON rule_embeddings
USING hnsw (embedding vector_cosine_ops)
"""
)
def downgrade() -> None:
op.execute("DROP INDEX IF EXISTS ix_rule_embeddings_embedding_hnsw")
op.drop_table("rule_embeddings")
+81
View File
@@ -0,0 +1,81 @@
/**
* Canonical systems — the GLOBAL area vocabulary every project's Systems can
* map onto (milestone 307).
*
* The mapping is an ASSOCIATION, never a rename: a project's System keeps the
* name the project gave it, and `canonical_id` only records which shared area
* it is an instance of. An unmapped System is fully usable — the catalog is a
* convergence aid, not a gate.
*/
import { apiGet, apiPost, apiPatch, apiPut } from "@/api/client";
export interface CanonicalSystem {
id: number;
name: string;
/** The match key: lowercase, "&" folded to "and", punctuation collapsed. */
slug: string;
description: string | null;
order_index: number;
created_at: string | null;
updated_at: string | null;
}
/**
* A suggested mapping. `basis` is the whole point of showing it:
* - `exact` — the names differ only in spelling. Mechanical.
* - `overlap` — they share a meaningful word. A judgment call the reviewer is
* making, and it must never be presented as if it were the first.
*/
export interface CanonicalMatch {
id: number;
name: string;
basis: "exact" | "overlap";
score?: number;
}
export interface MappingProposal {
system_id: number;
system_name: string;
canonical_id: number;
canonical_name: string;
basis: "exact" | "overlap";
score: number;
}
export async function listCanonicalSystems(): Promise<CanonicalSystem[]> {
const data = await apiGet<{ canonical_systems: CanonicalSystem[] }>(
"/api/canonical-systems",
);
return data.canonical_systems;
}
/** Admin only — a global list anyone can extend stops being shared. */
export async function createCanonicalSystem(data: {
name: string;
description?: string;
}): Promise<CanonicalSystem> {
return apiPost("/api/canonical-systems", data);
}
export async function updateCanonicalSystem(
id: number,
data: Partial<{ name: string; description: string; order_index: number }>,
): Promise<CanonicalSystem> {
return apiPatch(`/api/canonical-systems/${id}`, data);
}
/** Proposals for a project's UNMAPPED Systems. Reads only — nothing applied. */
export async function proposeMappings(projectId: number): Promise<MappingProposal[]> {
const data = await apiGet<{ proposals: MappingProposal[] }>(
`/api/projects/${projectId}/canonical-proposals`,
);
return data.proposals;
}
/** Apply or clear one mapping. `null` unmaps. */
export async function mapSystem(
systemId: number,
canonicalId: number | null,
): Promise<{ id: number; canonical_id: number | null }> {
return apiPut(`/api/systems/${systemId}/canonical`, { canonical_id: canonicalId });
}
+76 -14
View File
@@ -1,5 +1,24 @@
import { apiGet, apiPost, apiPatch, apiDelete } from "@/api/client";
/** How a rule reaches a session (milestone 307). */
export type RuleTier = "always_on" | "conditional";
/**
* A typed edge between two rules. Each kind exists because its absence forced
* a workaround: merging two rules into one row, writing an override as a
* near-copy, or leaving a local addendum with nothing to say it is one.
*/
export type RuleRelationKind = "co_surfaces" | "overrides" | "elaborates";
export interface RuleRelation {
id: number;
kind: RuleRelationKind;
/** The rule at the OTHER end. */
rule_id: number;
direction: "outgoing" | "incoming";
note: string;
}
export interface Rulebook {
id: number;
owner_user_id: number;
@@ -26,35 +45,53 @@ export interface Rule {
project_id: number | null;
title: string;
statement: string;
/** WHEN this rule fires — the trigger, not the instruction. */
when_to_apply: string;
/**
* always_on preloads into every session; conditional is reachable and
* surfaced when its trigger fires. A rule with no tier set behaves as
* always_on, which is how every rule behaved before this existed.
*/
tier: RuleTier;
why: string;
how_to_apply: string;
/** The note or task that caused this rule, if one was recorded. */
arose_from_id: number | null;
order_index: number;
created_at: string | null;
updated_at: string | null;
/** Present only when the rule has them (the server omits empty keys). */
systems?: { id: number; name: string }[];
relations?: RuleRelation[];
}
/**
* A rule as a LIST ROW — services.rulebooks.rule_brief's output. Carries the
* age deliberately: a rule written before the capability it duplicates is
* otherwise indistinguishable, at a glance, from one still doing work.
*/
export interface RuleHeader {
id: number;
title: string;
statement: string;
topic_id: number | null;
tier: RuleTier;
/** A date (YYYY-MM-DD), not a timestamp. */
updated_at: string | null;
when_to_apply?: string;
arose_from_id?: number;
}
export interface ApplicableRules {
rules: {
id: number;
title: string;
statement: string;
topic_id: number;
// Both lists are rule_brief's output — the SAME builder, so they are
// described the same way here rather than as two hand-written shapes that
// drift from it and from each other (which is what the server side had).
rules: (RuleHeader & {
topic_title: string;
rulebook_id: number;
rulebook_title: string;
}[];
project_rules: {
id: number;
title: string;
statement: string;
}[];
})[];
project_rules: RuleHeader[];
suppressed_rules: {
id: number;
title: string;
@@ -133,14 +170,39 @@ export async function getRule(id: number): Promise<Rule> {
return apiGet(`/api/rules/${id}`);
}
export async function createRule(topicId: number, data: { title: string; statement: string; why?: string; how_to_apply?: string; order_index?: number }): Promise<Rule> {
/** The fields both write paths accept. `system_ids` REPLACES a rule's areas. */
export interface RuleWrite {
title: string;
statement: string;
when_to_apply: string;
tier: RuleTier;
why: string;
how_to_apply: string;
order_index: number;
system_ids: number[];
arose_from_id: number | null;
}
export async function createRule(topicId: number, data: Partial<RuleWrite> & { title: string; statement: string }): Promise<Rule> {
return apiPost(`/api/rulebook-topics/${topicId}/rules`, data);
}
export async function updateRule(id: number, data: Partial<{ title: string; statement: string; why: string; how_to_apply: string; order_index: number }>): Promise<Rule> {
export async function updateRule(id: number, data: Partial<RuleWrite>): Promise<Rule> {
return apiPatch(`/api/rules/${id}`, data);
}
/** Draw a typed edge from one rule to another. Idempotent. */
export async function relateRules(
fromRuleId: number,
data: { to_rule_id: number; kind: RuleRelationKind; note?: string },
): Promise<{ id: number }> {
return apiPost(`/api/rules/${fromRuleId}/relations`, data);
}
export async function unrelateRules(relationId: number): Promise<void> {
return apiDelete(`/api/rule-relations/${relationId}`);
}
export async function deleteRule(id: number): Promise<void> {
return apiDelete(`/api/rules/${id}`);
}
@@ -161,7 +223,7 @@ export async function getProjectApplicableRules(projectId: number): Promise<Appl
export async function createProjectRule(
projectId: number,
data: { statement: string; title?: string; why?: string; how_to_apply?: string },
data: Partial<RuleWrite> & { statement: string },
): Promise<Rule> {
return apiPost(`/api/projects/${projectId}/rules`, data);
}
+21 -2
View File
@@ -1,9 +1,15 @@
import { apiGet, apiPost, apiPatch, apiDelete } from "@/api/client";
import type { CanonicalMatch } from "@/api/canonicalSystems";
export interface System {
id: number;
project_id: number;
name: string;
/**
* The global area this System is an instance of, or null. Null is a valid
* resting state — a project-specific area should stay unmapped.
*/
canonical_id: number | null;
description: string;
color: string | null;
status: "active" | "archived";
@@ -18,10 +24,23 @@ export async function listSystems(projectId: number): Promise<System[]> {
return data.systems;
}
/**
* A created System, plus the catalog's answer about its name. An `exact`
* catalog hit is applied by the server and arrives as a populated
* `canonical_id`; an `overlap` is only OFFERED, and comes back here for the
* caller to accept or ignore.
*
* A same-named System in this project is a 409 ApiError carrying
* `{duplicate, existing_id}` — the same gate the MCP door enforces (#2482).
*/
export interface CreatedSystem extends System {
canonical_suggestion?: CanonicalMatch;
}
export async function createSystem(
projectId: number,
data: { name: string; description?: string; color?: string },
): Promise<System> {
data: { name: string; description?: string; color?: string; canonical_id?: number },
): Promise<CreatedSystem> {
return apiPost(`/api/projects/${projectId}/systems`, data);
}
+253 -4
View File
@@ -1,14 +1,18 @@
<script setup lang="ts">
import { ref, computed, onMounted, watch } from "vue";
import { useSystemsStore } from "@/stores/systems";
import { useCanonicalSystemsStore } from "@/stores/canonicalSystems";
import { useToastStore } from "@/stores/toast";
import { getProjectIssues } from "@/api/systems";
import type { System, TaskLike } from "@/api/systems";
import type { CanonicalMatch } from "@/api/canonicalSystems";
import { apiErrorMessage } from "@/api/client";
import { Pencil, Trash2, Archive, ArchiveRestore } from "lucide-vue-next";
const props = defineProps<{ projectId: number }>();
const store = useSystemsStore();
const canon = useCanonicalSystemsStore();
const toast = useToastStore();
const error = ref<string | null>(null);
@@ -19,14 +23,26 @@ const issues = ref<TaskLike[]>([]);
const showCreate = ref(false);
const newName = ref("");
const newDescription = ref("");
// The global area, chosen explicitly. A PICKER rather than a live matcher on
// purpose: reproducing the server's slug rule in TypeScript would give this
// feature two matchers to keep in step, which is the exact drift the catalog
// exists to end. The server still applies an exact hit on submit.
const newCanonicalId = ref<number | null>(null);
const creating = ref(false);
// An `overlap` the server offered after a create — an offer, never applied.
const suggestion = ref<{ systemId: number; match: CanonicalMatch } | null>(null);
// Edit state
const editingId = ref<number | null>(null);
const editName = ref("");
const editDescription = ref("");
const editCanonicalId = ref<number | null>(null);
const savingEdit = ref(false);
// Mapping review
const showReview = ref(false);
const reviewBusy = ref<number | null>(null);
// Delete confirmation
const deletingSystem = ref<System | null>(null);
@@ -37,6 +53,12 @@ const visibleSystems = computed(() =>
showArchived.value ? systems.value : activeSystems.value,
);
const proposals = computed(() => canon.proposalsByProject[props.projectId] ?? []);
function areaName(system: System): string | null {
return canon.byId(system.canonical_id)?.name ?? null;
}
async function load() {
error.value = null;
try {
@@ -49,6 +71,14 @@ async function load() {
} catch {
issues.value = [];
}
// Both fail soft: the catalog is a naming aid, and a review prompt that
// cannot load must not take the Systems list down with it.
await canon.fetchCatalog();
try {
await canon.fetchProposals(props.projectId);
} catch {
/* no proposals shown */
}
}
onMounted(load);
@@ -58,12 +88,14 @@ function openCreate() {
showCreate.value = true;
newName.value = "";
newDescription.value = "";
newCanonicalId.value = null;
}
function cancelCreate() {
showCreate.value = false;
newName.value = "";
newDescription.value = "";
newCanonicalId.value = null;
}
async function submitCreate() {
@@ -71,23 +103,60 @@ async function submitCreate() {
if (!name || creating.value) return;
creating.value = true;
try {
await store.createSystem(props.projectId, {
const created = await store.createSystem(props.projectId, {
name,
description: newDescription.value.trim() || undefined,
canonical_id: newCanonicalId.value ?? undefined,
});
cancelCreate();
toast.show("System created");
} catch {
toast.show("Failed to create system", "error");
if (created.canonical_suggestion) {
// An overlap: shown as an offer beside the new System, never applied.
suggestion.value = { systemId: created.id, match: created.canonical_suggestion };
}
toast.show(
created.canonical_id
? `System created and filed under ${canon.byId(created.canonical_id)?.name}`
: "System created",
);
} catch (e) {
// 409 = this project already has that System. Say WHICH one, so the
// answer is actionable rather than "it didn't work".
toast.show(apiErrorMessage(e, "Failed to create system"), "error");
} finally {
creating.value = false;
}
}
async function acceptSuggestion() {
const pending = suggestion.value;
if (!pending) return;
suggestion.value = null;
try {
await canon.mapSystem(props.projectId, pending.systemId, pending.match.id);
await store.fetchSystems(props.projectId);
toast.show(`Filed under ${pending.match.name}`);
} catch {
/* the store already reported it */
}
}
async function applyProposal(systemId: number, canonicalId: number) {
reviewBusy.value = systemId;
try {
await canon.mapSystem(props.projectId, systemId, canonicalId);
await store.fetchSystems(props.projectId);
} catch {
/* the store already reported it */
} finally {
reviewBusy.value = null;
}
}
function startEdit(system: System) {
editingId.value = system.id;
editName.value = system.name;
editDescription.value = system.description;
editCanonicalId.value = system.canonical_id;
}
function cancelEdit() {
@@ -103,6 +172,12 @@ async function submitEdit(system: System) {
name,
description: editDescription.value.trim(),
});
// The mapping is a separate write with its own validation — one column,
// one writer (services/canonical_systems.set_system_canonical).
if (editCanonicalId.value !== system.canonical_id) {
await canon.mapSystem(props.projectId, system.id, editCanonicalId.value);
await store.fetchSystems(props.projectId);
}
editingId.value = null;
toast.show("System updated");
} catch {
@@ -161,6 +236,65 @@ async function confirmDelete() {
</ul>
</div>
<!-- Mapping review. Only appears when there is something to decide, and
it says HOW MANY rather than nagging with a permanent banner. -->
<div v-if="proposals.length" class="area-review">
<button class="area-review-head" @click="showReview = !showReview">
<span class="area-review-count">{{ proposals.length }}</span>
{{ proposals.length === 1 ? "system" : "systems" }} may belong to a shared area
<span class="area-review-chev">{{ showReview ? "▾" : "▸" }}</span>
</button>
<ul v-if="showReview" class="area-proposals">
<li v-for="p in proposals" :key="p.system_id" class="area-proposal">
<div class="area-proposal-text">
<span class="area-proposal-name">{{ p.system_name }}</span>
<span class="area-proposal-arrow" aria-hidden="true"></span>
<span class="area-proposal-target">{{ p.canonical_name }}</span>
<!-- The basis is the decision the reviewer is making: `exact`
differs only in spelling, `overlap` is a judgment call.
Showing them identically is how a wrong mapping is waved
through, so they never share a style. -->
<span
class="area-basis"
:class="p.basis === 'exact' ? 'area-basis--exact' : 'area-basis--overlap'"
:title="
p.basis === 'exact'
? 'Same name up to spelling — safe to accept.'
: 'Shares a word. Accept only if it is really the same area.'
"
>{{ p.basis === "exact" ? "same name" : "similar" }}</span>
</div>
<div class="area-proposal-actions">
<button
class="btn-primary btn-compact"
:disabled="reviewBusy === p.system_id"
@click="applyProposal(p.system_id, p.canonical_id)"
>
{{ reviewBusy === p.system_id ? "Filing…" : "File here" }}
</button>
<button
class="btn-ghost btn-compact"
@click="canon.dismissProposal(props.projectId, p.system_id)"
>
Not this
</button>
</div>
</li>
</ul>
</div>
<!-- An overlap offered by the server after a create. Never applied. -->
<div v-if="suggestion" class="area-offer">
<span>
Is this the same area as
<strong>{{ suggestion.match.name }}</strong>?
</span>
<div class="area-proposal-actions">
<button class="btn-primary btn-compact" @click="acceptSuggestion">File it there</button>
<button class="btn-ghost btn-compact" @click="suggestion = null">No, it's ours</button>
</div>
</div>
<!-- Toolbar -->
<div class="systems-toolbar">
<button v-if="!showCreate" class="btn-ghost btn-inline btn-add-system" @click="openCreate">
@@ -189,6 +323,20 @@ async function confirmDelete() {
placeholder="What is this subsystem responsible for? (optional)"
aria-label="System description"
></textarea>
<label v-if="canon.catalog.length" class="area-field">
<span class="area-label">Shared area</span>
<select v-model="newCanonicalId" class="fs-input area-select" aria-label="Shared area">
<option :value="null">None specific to this project</option>
<option v-for="entry in canon.catalog" :key="entry.id" :value="entry.id">
{{ entry.name }}
</option>
</select>
<!-- .field-hint is the shared hint class beside .fs-input
(components.css) not restated scoped. -->
<span class="field-hint">
Files this system under an area shared by every project. Your name stays as you typed it.
</span>
</label>
<div class="system-form-actions">
<button type="submit" class="btn-primary btn-compact" :disabled="!newName.trim() || creating">
{{ creating ? "Creating…" : "Create" }}
@@ -240,6 +388,15 @@ async function confirmDelete() {
placeholder="Description (optional)"
aria-label="System description"
></textarea>
<label v-if="canon.catalog.length" class="area-field">
<span class="area-label">Shared area</span>
<select v-model="editCanonicalId" class="fs-input area-select" aria-label="Shared area">
<option :value="null">None specific to this project</option>
<option v-for="entry in canon.catalog" :key="entry.id" :value="entry.id">
{{ entry.name }}
</option>
</select>
</label>
<div class="system-form-actions">
<button type="submit" class="btn-primary btn-compact" :disabled="!editName.trim() || savingEdit">
{{ savingEdit ? "Saving…" : "Save" }}
@@ -264,6 +421,13 @@ async function confirmDelete() {
:title="`${system.open_issue_count} open issue(s)`"
>{{ system.open_issue_count }} open</span>
<span v-if="system.status === 'archived'" class="archived-badge">Archived</span>
<!-- Not a TagPill: that recipe prefixes "#" and means a tag.
This is the shared AREA this system is an instance of. -->
<span
v-if="areaName(system)"
class="area-chip"
:title="`Filed under the shared area “${areaName(system)}” — records and rules about this area line up across projects.`"
>{{ areaName(system) }}</span>
</div>
<p v-if="system.description" class="system-description">{{ system.description }}</p>
</div>
@@ -335,6 +499,91 @@ async function confirmDelete() {
.issue-systems { display: flex; gap: 0.25rem; flex-shrink: 0; flex-wrap: wrap; }
.issue-sys-chip { font-size: 0.66rem; color: var(--fs-text-secondary); background: var(--fs-surface-raised); border-radius: 999px; padding: 0.05rem 0.4rem; }
/* ── Shared-area mapping (milestone 307) ──────────────────────────
The review is a disclosure, not a banner: it exists only while there is
something to decide, and collapses to one line until opened. */
.area-review {
border: 1px solid var(--fs-border-color);
border-radius: var(--fs-radius-lg);
background: var(--fs-surface-raised);
}
.area-review-head {
display: flex;
align-items: center;
gap: var(--fs-space-2);
width: 100%;
padding: var(--fs-space-3);
background: none;
border: none;
color: var(--fs-text-secondary);
font: inherit;
font-size: 0.82rem;
text-align: left;
cursor: pointer;
border-radius: var(--fs-radius-lg);
}
.area-review-head:hover { color: var(--fs-text-primary); }
.area-review-head:focus-visible { outline: none; box-shadow: var(--fs-focus-ring); }
.area-review-count {
background: var(--fs-accent-soft);
color: var(--fs-accent);
border-radius: var(--fs-radius-pill);
padding: 0.05rem 0.45rem;
font-variant-numeric: tabular-nums;
}
.area-review-chev { margin-left: auto; color: var(--fs-text-tertiary); }
.area-proposals { list-style: none; margin: 0; padding: 0 var(--fs-space-3) var(--fs-space-3); display: flex; flex-direction: column; gap: var(--fs-space-2); }
.area-proposal {
display: flex;
align-items: center;
justify-content: space-between;
gap: var(--fs-space-3);
flex-wrap: wrap;
padding: var(--fs-space-2) var(--fs-space-3);
background: var(--fs-surface-page);
border: 1px solid var(--fs-border-color);
border-radius: var(--fs-radius-md);
}
.area-proposal-text { display: flex; align-items: center; gap: var(--fs-space-2); flex-wrap: wrap; font-size: 0.85rem; min-width: 0; }
.area-proposal-name { color: var(--fs-text-primary); }
.area-proposal-arrow { color: var(--fs-text-tertiary); }
.area-proposal-target { color: var(--fs-accent); }
.area-proposal-actions { display: flex; gap: var(--fs-space-2); flex-shrink: 0; }
/* The two bases must never look alike — one is mechanical, the other is the
reviewer's judgment, and that difference is the whole decision. */
.area-basis { font-size: 0.68rem; border-radius: var(--fs-radius-sm); padding: 0.05rem 0.4rem; }
.area-basis--exact { background: var(--fs-status-done-bg); color: var(--fs-status-done); }
.area-basis--overlap { background: var(--fs-priority-medium-bg); color: var(--fs-priority-medium); }
.area-offer {
display: flex;
align-items: center;
justify-content: space-between;
gap: var(--fs-space-3);
flex-wrap: wrap;
padding: var(--fs-space-3);
font-size: 0.85rem;
color: var(--fs-text-secondary);
background: var(--fs-accent-faint);
border: 1px solid var(--fs-border-color);
border-radius: var(--fs-radius-lg);
}
.area-field { display: flex; flex-direction: column; gap: 0.3rem; }
.area-label { font-size: 0.78rem; color: var(--fs-text-tertiary); }
.area-select { box-sizing: border-box; width: 100%; }
.area-chip {
font-size: 0.66rem;
color: var(--fs-accent);
background: var(--fs-accent-soft);
border-radius: var(--fs-radius-pill);
padding: 0.05rem 0.45rem;
white-space: nowrap;
}
/* ── Toolbar ──────────────────────────────────────────────────── */
.systems-toolbar { display: flex; align-items: center; justify-content: space-between; gap: 0.75rem; }
.btn-add-system {
@@ -27,7 +27,10 @@ const expandedRuleIds = ref<Set<number>>(new Set());
const ruleDetails = ref<Record<number, { why: string; how_to_apply: string }>>({});
const showProjectRuleForm = ref(false);
const newProjectRule = ref({ title: "", statement: "", why: "", how_to_apply: "" });
const newProjectRule = ref({
title: "", statement: "", why: "", how_to_apply: "",
when_to_apply: "", tier: "always_on" as "always_on" | "conditional",
});
async function load() {
applicable.value = await getProjectApplicableRules(props.projectId);
@@ -90,14 +93,20 @@ interface RulebookGroup {
function groupByRulebookAndTopic(rules: ApplicableRules["rules"]): RulebookGroup[] {
const byRulebook = new Map<number, RulebookGroup>();
for (const r of rules) {
// A rule carries topic_id XOR project_id. Only rulebook-scoped rules reach
// this list, so a null topic would be a server-side contradiction — skip
// it rather than widen the group's type to accommodate a case that means
// something is wrong upstream.
if (r.topic_id === null) continue;
const topicId = r.topic_id;
let rb = byRulebook.get(r.rulebook_id);
if (!rb) {
rb = { rulebook_id: r.rulebook_id, rulebook_title: r.rulebook_title, topics: [] };
byRulebook.set(r.rulebook_id, rb);
}
let topic = rb.topics.find((t) => t.topic_id === r.topic_id);
let topic = rb.topics.find((t) => t.topic_id === topicId);
if (!topic) {
topic = { topic_id: r.topic_id, topic_title: r.topic_title, rules: [] };
topic = { topic_id: topicId, topic_title: r.topic_title, rules: [] };
rb.topics.push(topic);
}
topic.rules.push(r);
@@ -113,8 +122,13 @@ async function submitProjectRule() {
title: newProjectRule.value.title.trim() || undefined,
why: newProjectRule.value.why.trim() || undefined,
how_to_apply: newProjectRule.value.how_to_apply.trim() || undefined,
when_to_apply: newProjectRule.value.when_to_apply.trim() || undefined,
tier: newProjectRule.value.tier,
});
newProjectRule.value = { title: "", statement: "", why: "", how_to_apply: "" };
newProjectRule.value = {
title: "", statement: "", why: "", how_to_apply: "",
when_to_apply: "", tier: "always_on",
};
showProjectRuleForm.value = false;
await load();
}
@@ -219,6 +233,24 @@ watch(() => props.projectId, load);
placeholder="Statement (required) — the actionable instruction, 1-2 sentences"
rows="2"
></textarea>
<textarea
v-model="newProjectRule.when_to_apply"
placeholder="When to apply — the trigger, not the instruction"
rows="2"
></textarea>
<div class="tier-row">
<label>
<input v-model="newProjectRule.tier" type="radio" value="always_on" />
Always on
</label>
<label>
<input v-model="newProjectRule.tier" type="radio" value="conditional" />
Conditional
</label>
<span class="tier-hint">
Conditional if you had to name a system, an artifact or a moment to state the trigger.
</span>
</div>
<textarea
v-model="newProjectRule.why"
placeholder="Why (optional) — the rationale"
@@ -345,6 +377,11 @@ watch(() => props.projectId, load);
</template>
<style scoped>
.tier-row { display: flex; align-items: center; gap: 0.75rem; flex-wrap: wrap; font-size: 0.85rem; }
.tier-row label { display: inline-flex; align-items: center; gap: 0.3rem; }
.tier-row input { accent-color: var(--fs-accent); }
.tier-hint { flex: 1; min-width: 12rem; font-size: 0.75rem; color: var(--fs-text-tertiary); }
.excluded-note { margin: 0 0 0.5rem; color: var(--fs-text-tertiary); font-size: 0.85rem; }
.chip-excluded { opacity: 0.8; text-decoration: line-through; }
.chip-excluded .chip-remove { text-decoration: none; }
@@ -1,16 +1,41 @@
<script setup lang="ts">
import { ref, watch, onMounted } from "vue";
import { computed, ref, watch, onMounted } from "vue";
import { useRulebooksStore } from "@/stores/rulebooks";
import { useCanonicalSystemsStore } from "@/stores/canonicalSystems";
import type { RuleTier } from "@/api/rulebooks";
const props = defineProps<{ ruleId: number | null; topicId: number | null }>();
const emit = defineEmits<{ close: [] }>();
const store = useRulebooksStore();
const canon = useCanonicalSystemsStore();
const title = ref("");
const statement = ref("");
const whenToApply = ref("");
const tier = ref<RuleTier>("always_on");
const systemIds = ref<number[]>([]);
const why = ref("");
const howToApply = ref("");
const relations = computed(() => store.currentRule?.relations ?? []);
// The label a reader needs to judge an edge, not the stored token.
const RELATION_LABEL: Record<string, { outgoing: string; incoming: string }> = {
co_surfaces: { outgoing: "arrives with", incoming: "arrives with" },
overrides: { outgoing: "overrides", incoming: "is overridden by" },
elaborates: { outgoing: "elaborates", incoming: "is elaborated by" },
};
function relationLabel(kind: string, direction: "outgoing" | "incoming") {
return RELATION_LABEL[kind]?.[direction] ?? kind;
}
function toggleSystem(id: number) {
const at = systemIds.value.indexOf(id);
if (at >= 0) systemIds.value.splice(at, 1);
else systemIds.value.push(id);
}
const isCreating = ref(props.ruleId === null);
async function load() {
@@ -20,15 +45,22 @@ async function load() {
if (r) {
title.value = r.title;
statement.value = r.statement;
whenToApply.value = r.when_to_apply || "";
tier.value = r.tier || "always_on";
systemIds.value = (r.systems ?? []).map((sys) => sys.id);
why.value = r.why || "";
howToApply.value = r.how_to_apply || "";
}
} else {
title.value = "";
statement.value = "";
whenToApply.value = "";
tier.value = "always_on";
systemIds.value = [];
why.value = "";
howToApply.value = "";
}
await canon.fetchCatalog();
}
async function save() {
@@ -36,16 +68,21 @@ async function save() {
emit("close");
return;
}
const fields = {
title: title.value,
statement: statement.value,
when_to_apply: whenToApply.value,
tier: tier.value,
// Always sent, so clearing the last area actually clears it — the server
// reads a list as "these ARE the areas now".
system_ids: systemIds.value,
why: why.value,
how_to_apply: howToApply.value,
};
if (isCreating.value && props.topicId !== null) {
await store.createRule(props.topicId, {
title: title.value, statement: statement.value,
why: why.value, how_to_apply: howToApply.value,
});
await store.createRule(props.topicId, fields);
} else if (props.ruleId !== null) {
await store.updateRule(props.ruleId, {
title: title.value, statement: statement.value,
why: why.value, how_to_apply: howToApply.value,
});
await store.updateRule(props.ruleId, fields);
}
emit("close");
}
@@ -77,6 +114,69 @@ watch(() => props.ruleId, load);
Statement <span class="required">*</span>
<textarea v-model="statement" rows="3" placeholder="The actionable instruction (1-2 sentences)." />
</label>
<label>
When to apply
<textarea
v-model="whenToApply"
rows="2"
placeholder="The trigger, not the instruction — “before any git push”, “when a release is being cut”."
/>
</label>
<fieldset class="tier">
<legend>How it reaches a session</legend>
<label class="tier-opt">
<input v-model="tier" type="radio" value="always_on" />
<span>
<strong>Always on</strong>
loaded into every session.
</span>
</label>
<label class="tier-opt">
<input v-model="tier" type="radio" value="conditional" />
<span>
<strong>Conditional</strong>
arrives when its trigger fires.
</span>
</label>
<p class="tier-test">
The test: can you name the trigger <em>without</em> naming a system, an artifact type
or a moment? If the honest answer is whenever you are working, it is always on.
Conditional costs nothing when it is irrelevant, which is what lets it be as long as
it needs to be.
</p>
</fieldset>
<fieldset v-if="canon.catalog.length" class="areas">
<legend>Areas this rule is about</legend>
<label v-for="entry in canon.catalog" :key="entry.id" class="area-opt">
<input
type="checkbox"
:checked="systemIds.includes(entry.id)"
@change="toggleSystem(entry.id)"
/>
<span>{{ entry.name }}</span>
</label>
<p class="tier-test">
What lets this rule reach a project working in that area.
</p>
</fieldset>
<section v-if="relations.length" class="relations">
<h3>Related rules</h3>
<ul>
<li v-for="rel in relations" :key="rel.id" class="relation">
<span class="relation-kind">{{ relationLabel(rel.kind, rel.direction) }}</span>
<span class="relation-target">rule #{{ rel.rule_id }}</span>
<span v-if="rel.note" class="relation-note">{{ rel.note }}</span>
</li>
</ul>
<p class="tier-test">
Rules that <em>fail together</em> are linked, never merged a merged rule cannot be
cited, surfaced or suppressed a clause at a time.
</p>
</section>
<label>
Why
<textarea v-model="why" rows="4" placeholder="Rationale — the reason this rule exists." />
@@ -118,6 +218,19 @@ input, textarea {
padding: 0.5rem; font: inherit;
font-family: inherit;
}
fieldset { border: 1px solid var(--fs-border-color); border-radius: var(--fs-radius-md); padding: 0.75rem; margin-bottom: 1rem; }
legend { padding: 0 0.35rem; font-size: 0.8rem; color: var(--fs-text-tertiary); }
.tier-opt, .area-opt { display: flex; align-items: flex-start; gap: 0.5rem; margin-bottom: 0.4rem; font-size: 0.88rem; }
.tier-opt input, .area-opt input { width: auto; margin-top: 0.2rem; accent-color: var(--fs-accent); }
.tier-test { margin: 0.5rem 0 0; font-size: 0.78rem; color: var(--fs-text-tertiary); line-height: 1.45; }
.relations h3 { margin: 0 0 0.5rem; font-size: 0.85rem; color: var(--fs-text-secondary); }
.relations ul { list-style: none; margin: 0; padding: 0; display: flex; flex-direction: column; gap: 0.35rem; }
.relation { display: flex; align-items: baseline; gap: 0.4rem; flex-wrap: wrap; font-size: 0.85rem; }
.relation-kind { color: var(--fs-accent); }
.relation-target { color: var(--fs-text-primary); }
.relation-note { width: 100%; font-size: 0.78rem; color: var(--fs-text-tertiary); }
.trash, .close { background: none; border: none; cursor: pointer; opacity: 0.6; font-size: 1.25em; }
.trash:hover, .close:hover { opacity: 1; }
</style>
+24 -1
View File
@@ -13,8 +13,17 @@ const emit = defineEmits<{
<header><h2>Rules</h2></header>
<ul>
<li v-for="r in rules" :key="r.id" @click="emit('open-rule', r.id)">
<div class="title">{{ r.title }}</div>
<div class="title">
{{ r.title }}
<!-- Only conditional is marked: always-on is the default and
badging every row would say nothing. -->
<span v-if="r.tier === 'conditional'" class="tier-chip" title="Arrives when its trigger fires, rather than in every session">conditional</span>
</div>
<div class="statement">{{ r.statement }}</div>
<div v-if="r.when_to_apply || r.updated_at" class="meta">
<span v-if="r.when_to_apply" class="trigger">{{ r.when_to_apply }}</span>
<span v-if="r.updated_at" class="age" :title="`Last changed ${r.updated_at}`">{{ r.updated_at }}</span>
</div>
</li>
</ul>
<button class="new-rule" @click="emit('create-rule', topicId)">+ New rule</button>
@@ -35,5 +44,19 @@ li {
li:hover { background: var(--fs-surface-hover); }
.title { font-family: Fraunces, serif; font-style: italic; font-size: 1.05em; }
.statement { font-size: 0.9em; opacity: 0.8; margin-top: 0.25rem; }
.meta { display: flex; align-items: baseline; gap: 0.5rem; margin-top: 0.35rem; font-size: 0.75em; }
.trigger { flex: 1; min-width: 0; color: var(--fs-text-secondary); overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
.age { color: var(--fs-text-tertiary); font-variant-numeric: tabular-nums; flex-shrink: 0; }
.tier-chip {
margin-left: 0.4rem;
font-family: var(--fs-font-body);
font-style: normal;
font-size: 0.62rem;
color: var(--fs-text-secondary);
background: var(--fs-surface-raised);
border-radius: var(--fs-radius-pill);
padding: 0.05rem 0.4rem;
vertical-align: middle;
}
.new-rule { cursor: pointer; }
</style>
+93
View File
@@ -0,0 +1,93 @@
import { ref } from "vue";
import { defineStore } from "pinia";
import * as api from "@/api/canonicalSystems";
import type { CanonicalSystem, MappingProposal } from "@/api/canonicalSystems";
import { useToastStore } from "@/stores/toast";
import { apiErrorMessage } from "@/api/client";
/**
* The global area catalog (milestone 307). Shared by every project, so it is
* fetched ONCE per session rather than per project — the whole point of the
* table is that it is the same list everywhere.
*/
export const useCanonicalSystemsStore = defineStore("canonicalSystems", () => {
const catalog = ref<CanonicalSystem[]>([]);
const loaded = ref(false);
const loading = ref(false);
const proposalsByProject = ref<Record<number, MappingProposal[]>>({});
async function fetchCatalog(force = false) {
if (loaded.value && !force) return catalog.value;
loading.value = true;
try {
catalog.value = await api.listCanonicalSystems();
loaded.value = true;
} catch {
// A naming aid must never break the screen it rides on — an empty
// catalog degrades the suggestion, it does not fail the form.
catalog.value = [];
} finally {
loading.value = false;
}
return catalog.value;
}
function byId(id: number | null): CanonicalSystem | undefined {
if (id == null) return undefined;
return catalog.value.find((c) => c.id === id);
}
async function fetchProposals(projectId: number) {
proposalsByProject.value[projectId] = await api.proposeMappings(projectId);
return proposalsByProject.value[projectId];
}
/** Apply or clear one mapping, then drop it from the pending proposals. */
async function mapSystem(projectId: number, systemId: number, canonicalId: number | null) {
try {
await api.mapSystem(systemId, canonicalId);
} catch (e) {
useToastStore().show(apiErrorMessage(e, "Failed to map system"), "error");
throw e;
}
dismissProposal(projectId, systemId);
}
/** Remove a proposal from the pending list without writing anything. */
function dismissProposal(projectId: number, systemId: number) {
const list = proposalsByProject.value[projectId];
if (list) {
proposalsByProject.value[projectId] = list.filter((p) => p.system_id !== systemId);
}
}
async function createEntry(data: { name: string; description?: string }) {
const entry = await api.createCanonicalSystem(data);
catalog.value.push(entry);
return entry;
}
async function updateEntry(
id: number,
data: Partial<{ name: string; description: string; order_index: number }>,
) {
const entry = await api.updateCanonicalSystem(id, data);
const idx = catalog.value.findIndex((c) => c.id === id);
if (idx >= 0) catalog.value[idx] = entry;
return entry;
}
return {
catalog,
loaded,
loading,
proposalsByProject,
fetchCatalog,
byId,
fetchProposals,
mapSystem,
dismissProposal,
createEntry,
updateEntry,
};
});
+40 -8
View File
@@ -35,9 +35,7 @@ export const useRulebooksStore = defineStore("rulebooks", () => {
async function fetchRules(topicId: number) {
try {
const rules = await api.listRules({ topic_id: topicId });
rulesByTopic.value[topicId] = rules.map((r) => ({
id: r.id, title: r.title, statement: r.statement, topic_id: r.topic_id,
}));
rulesByTopic.value[topicId] = rules.map(toHeader);
} catch (e) {
useToastStore().show("Failed to load rules", "error");
throw e;
@@ -98,24 +96,58 @@ export const useRulebooksStore = defineStore("rulebooks", () => {
delete rulesByTopic.value[id];
}
async function createRule(topicId: number, data: { title: string; statement: string; why?: string; how_to_apply?: string }) {
/**
* A list row built from a full rule. The row shape is the server's
* rule_brief, so every field it carries has to be mirrored here or the two
* disagree the moment a list is patched locally instead of re-fetched.
*/
function toHeader(rule: Rule): api.RuleHeader {
return {
id: rule.id,
title: rule.title,
statement: rule.statement,
topic_id: rule.topic_id,
tier: rule.tier,
updated_at: rule.updated_at,
when_to_apply: rule.when_to_apply || undefined,
arose_from_id: rule.arose_from_id ?? undefined,
};
}
async function createRule(topicId: number, data: Partial<api.RuleWrite> & { title: string; statement: string }) {
const rule = await api.createRule(topicId, data);
if (!rulesByTopic.value[topicId]) rulesByTopic.value[topicId] = [];
rulesByTopic.value[topicId].push({ id: rule.id, title: rule.title, statement: rule.statement, topic_id: rule.topic_id });
rulesByTopic.value[topicId].push(toHeader(rule));
return rule;
}
async function updateRule(id: number, data: Partial<Pick<Rule, "title" | "statement" | "why" | "how_to_apply" | "order_index">>) {
async function updateRule(id: number, data: Partial<api.RuleWrite>) {
const rule = await api.updateRule(id, data);
if (currentRule.value?.id === id) currentRule.value = rule;
for (const tid of Object.keys(rulesByTopic.value)) {
const list = rulesByTopic.value[Number(tid)];
const idx = list.findIndex((r) => r.id === id);
if (idx >= 0) list[idx] = { id: rule.id, title: rule.title, statement: rule.statement, topic_id: rule.topic_id };
if (idx >= 0) list[idx] = toHeader(rule);
}
return rule;
}
async function relateRules(
fromRuleId: number,
data: { to_rule_id: number; kind: api.RuleRelationKind; note?: string },
) {
await api.relateRules(fromRuleId, data);
// Re-read rather than patching locally: the edge reads from BOTH ends, so
// the far rule's relations changed too and a local splice would show only
// half of what just happened.
await fetchRule(fromRuleId);
}
async function unrelateRules(relationId: number, refreshRuleId: number) {
await api.unrelateRules(relationId);
await fetchRule(refreshRuleId);
}
async function deleteRule(id: number) {
await api.deleteRule(id);
if (currentRule.value?.id === id) currentRule.value = null;
@@ -129,6 +161,6 @@ export const useRulebooksStore = defineStore("rulebooks", () => {
fetchRulebooks, fetchTopics, fetchRules, fetchRule,
createRulebook, updateRulebook, toggleAlwaysOn, deleteRulebook,
createTopic, updateTopic, deleteTopic,
createRule, updateRule, deleteRule,
createRule, updateRule, deleteRule, relateRules, unrelateRules,
};
});
+1 -1
View File
@@ -22,7 +22,7 @@ export const useSystemsStore = defineStore("systems", () => {
async function createSystem(
projectId: number,
data: { name: string; description?: string; color?: string },
data: { name: string; description?: string; color?: string; canonical_id?: number },
) {
const system = await api.createSystem(projectId, data);
if (!systemsByProject.value[projectId]) systemsByProject.value[projectId] = [];
+162 -2
View File
@@ -3,6 +3,7 @@ import { ref, computed, watch, onMounted } from "vue";
import { useSettingsStore } from "@/stores/settings";
import { useAuthStore } from "@/stores/auth";
import { useToastStore } from "@/stores/toast";
import { useCanonicalSystemsStore } from "@/stores/canonicalSystems";
import { apiGet, apiPost, apiPut, apiDelete, listGroups, createGroup, deleteGroup, listGroupMembers, addGroupMember, removeGroupMember, searchUsers, listApiKeys, createApiKey as apiCreateApiKey, revokeApiKey as apiRevokeApiKey, getProfile, updateProfile, type ApiKeyEntry, type GroupEntry, type GroupMember, type UserSearchResult, type UserProfile, apiErrorMessage } from "@/api/client";
import type { User } from "@/types/auth";
import PaginationBar from "@/components/PaginationBar.vue";
@@ -12,6 +13,62 @@ import { fmtDate, fmtLogStamp } from "@/utils/dateFormat";
const store = useSettingsStore();
const authStore = useAuthStore();
const toastStore = useToastStore();
// ── Shared areas (milestone 307) ────────────────────────────────────────
// The global vocabulary a project's Systems map onto. Admin-only to WRITE —
// a global list anyone can extend stops being a shared list — but every user
// reads it, which is why the catalog lives in a store rather than here.
const canonStore = useCanonicalSystemsStore();
const newAreaName = ref("");
const newAreaDescription = ref("");
const creatingArea = ref(false);
const editingAreaId = ref<number | null>(null);
const editAreaName = ref("");
const editAreaDescription = ref("");
const savingArea = ref(false);
async function createArea() {
const name = newAreaName.value.trim();
if (!name || creatingArea.value) return;
creatingArea.value = true;
try {
await canonStore.createEntry({
name,
description: newAreaDescription.value.trim() || undefined,
});
newAreaName.value = "";
newAreaDescription.value = "";
toastStore.show("Area added");
} catch (e) {
// A 409 means an area with the same match key already exists — say which,
// because "CI and Release" vs "CI & Release" looks like a different name.
toastStore.show(apiErrorMessage(e, "Failed to add area"), "error");
} finally {
creatingArea.value = false;
}
}
function startEditArea(id: number, name: string, description: string | null) {
editingAreaId.value = id;
editAreaName.value = name;
editAreaDescription.value = description ?? "";
}
async function saveArea() {
const id = editingAreaId.value;
const name = editAreaName.value.trim();
if (id == null || !name || savingArea.value) return;
savingArea.value = true;
try {
await canonStore.updateEntry(id, { name, description: editAreaDescription.value.trim() });
editingAreaId.value = null;
toastStore.show("Area updated");
} catch (e) {
toastStore.show(apiErrorMessage(e, "Failed to update area"), "error");
} finally {
savingArea.value = false;
}
}
const userTimezone = ref("");
const savingTimezone = ref(false);
const timezoneSaved = ref(false);
@@ -134,7 +191,7 @@ const appVersion = ref('dev');
const restoreFileInput = ref<HTMLInputElement | null>(null);
// Migrate stored "admin" → "config"; unknown tabs fall back to "general"
const VALID_TABS = new Set(["general", "account", "profile", "notifications", "integrations", "data", "apikeys", "config", "users", "logs", "groups"]);
const VALID_TABS = new Set(["general", "account", "profile", "notifications", "integrations", "data", "apikeys", "config", "users", "logs", "groups", "areas"]);
const _stored = localStorage.getItem("settings_tab") ?? "general";
const activeTab = ref(VALID_TABS.has(_stored) ? (_stored === "admin" ? "config" : _stored) : "general");
@@ -143,6 +200,7 @@ function _loadTabContent(tab: string) {
if (tab === "users") loadUsersPanel();
else if (tab === "logs") loadLogsPanel();
else if (tab === "groups") loadGroupsPanel();
else if (tab === "areas") canonStore.fetchCatalog(true);
}
if (tab === "apikeys") { fetchApiKeys(); }
}
@@ -1212,7 +1270,7 @@ async function deleteUser(userId: number) {
<div v-if="authStore.isAdmin" class="sidebar-group">
<div class="sidebar-group-label">Admin</div>
<button
v-for="tab in ['config', 'users', 'groups', 'logs']"
v-for="tab in ['config', 'areas', 'users', 'groups', 'logs']"
:key="tab"
:class="['sidebar-item', { active: activeTab === tab }]"
@click="activeTab = tab"
@@ -2263,6 +2321,78 @@ async function deleteUser(userId: number) {
</div>
<!-- Users -->
<!-- Shared areas -->
<div v-if="authStore.isAdmin" v-show="activeTab === 'areas'" class="settings-grid">
<section class="settings-section full-width">
<h2>Shared areas</h2>
<p class="field-hint">
The vocabulary every project's Systems can be filed under, so the same word means the
same thing everywhere. A project keeps its own name for an area — mapping records which
shared area it is, it never renames anything. Editing a name here re-derives its match
key, so existing mappings are kept but future name matching follows the new spelling.
</p>
<ul class="area-admin-list">
<li v-for="entry in canonStore.catalog" :key="entry.id" class="area-admin-row">
<template v-if="editingAreaId === entry.id">
<form class="area-admin-form" @submit.prevent="saveArea">
<input v-model="editAreaName" class="fs-input" aria-label="Area name" />
<textarea
v-model="editAreaDescription"
class="fs-input"
rows="2"
aria-label="Area description"
></textarea>
<div class="area-admin-actions">
<button type="submit" class="btn-primary btn-compact" :disabled="!editAreaName.trim() || savingArea">
{{ savingArea ? "Saving…" : "Save" }}
</button>
<button type="button" class="btn-ghost btn-compact" @click="editingAreaId = null">Cancel</button>
</div>
</form>
</template>
<template v-else>
<div class="area-admin-body">
<div class="area-admin-name-row">
<span class="area-admin-name">{{ entry.name }}</span>
<code class="area-admin-slug" title="The match key. Names that reduce to this are the same area.">{{ entry.slug }}</code>
</div>
<p v-if="entry.description" class="area-admin-desc">{{ entry.description }}</p>
</div>
<button
class="btn-ghost btn-compact"
@click="startEditArea(entry.id, entry.name, entry.description)"
>Edit</button>
</template>
</li>
</ul>
<p v-if="!canonStore.catalog.length && !canonStore.loading" class="settings-empty">
No areas yet.
</p>
<form class="area-admin-form area-admin-create" @submit.prevent="createArea">
<input
v-model="newAreaName"
class="fs-input"
placeholder="New area name (e.g. Search &amp; Indexing)"
aria-label="New area name"
/>
<textarea
v-model="newAreaDescription"
class="fs-input"
rows="2"
placeholder="What belongs in this area? One paragraph — a bare name is never enough."
aria-label="New area description"
></textarea>
<div class="area-admin-actions">
<button type="submit" class="btn-primary btn-compact" :disabled="!newAreaName.trim() || creatingArea">
{{ creatingArea ? "Adding…" : "Add area" }}
</button>
</div>
</form>
</section>
</div>
<div v-if="authStore.isAdmin" v-show="activeTab === 'users'" class="settings-grid">
<section class="settings-section full-width">
@@ -3401,4 +3531,34 @@ async function deleteUser(userId: number) {
color: var(--fs-accent);
font-weight: 500;
}
/* ── Shared areas (milestone 307) ──────────────────────────────────
The slug is shown deliberately: it is what decides whether two names are
the same area, and an admin renaming an entry needs to see it move. */
.area-admin-list { list-style: none; margin: 1rem 0 0; padding: 0; display: flex; flex-direction: column; gap: var(--fs-space-2); }
.area-admin-row {
display: flex;
align-items: flex-start;
justify-content: space-between;
gap: var(--fs-space-3);
padding: var(--fs-space-3);
background: var(--fs-surface-raised);
border: 1px solid var(--fs-border-color);
border-radius: var(--fs-radius-md);
}
.area-admin-body { flex: 1; min-width: 0; }
.area-admin-name-row { display: flex; align-items: baseline; gap: var(--fs-space-2); flex-wrap: wrap; }
.area-admin-name { color: var(--fs-text-primary); }
.area-admin-slug {
font-family: var(--fs-font-mono);
font-size: 0.72rem;
color: var(--fs-text-tertiary);
background: var(--fs-surface-code-inline);
border-radius: var(--fs-radius-sm);
padding: 0.05rem 0.35rem;
}
.area-admin-desc { margin: 0.35rem 0 0; font-size: 0.85rem; color: var(--fs-text-secondary); }
.area-admin-form { display: flex; flex-direction: column; gap: 0.5rem; flex: 1; }
.area-admin-create { margin-top: var(--fs-space-4); }
.area-admin-actions { display: flex; gap: 0.4rem; }
</style>
+8 -4
View File
@@ -1,13 +1,17 @@
{
"name": "scribe",
"description": "Scribe system-of-record for Claude Code: MCP tools over your notes/tasks/projects/rules, a session-start push channel that surfaces your always-on rules + active-project context, process-skills (writing-plans, systematic-debugging, verification, brainstorming, reusing-code), and your saved Scribe Processes auto-surfaced as skills (/scribe:sync). Replaces superpowers + file-memory with one app-backed plugin.",
"version": "0.1.46",
"author": { "name": "Bryan Van Deusen" },
"version": "0.1.47",
"author": {
"name": "Bryan Van Deusen"
},
"mcpServers": {
"scribe": {
"type": "http",
"url": "${user_config.api_endpoint}/mcp",
"headers": { "Authorization": "Bearer ${user_config.api_token}" }
"headers": {
"Authorization": "Bearer ${user_config.api_token}"
}
}
},
"userConfig": {
@@ -19,7 +23,7 @@
"api_token": {
"type": "string",
"title": "Scribe API key",
"description": "An fmcp_ API key from Settings API Keys (read scope is enough for the session-start hook; write scope to use the tools)",
"description": "An fmcp_ API key from Settings \u2192 API Keys (read scope is enough for the session-start hook; write scope to use the tools)",
"sensitive": true
}
}
+15 -1
View File
@@ -174,17 +174,24 @@ mkdir -p "$state_dir" 2>/dev/null || true
# (a derive group id) or a canon elsewhere (`canon:<snippet_id>`) for the
# shapes being written. Keyed by that token, not a note id, so it dedups on
# its own file and a family is named once per session, not at every edit.
#
# A FOURTH channel (milestone 307): standing RULES the write resembles. Its own
# file for the same reason as the others — a rule named once should not be
# re-offered on every subsequent write in the session.
idfile=""
syncfile=""
derivefile=""
rulefile=""
exclude_q=""
sync_exclude_q=""
derive_exclude_q=""
rule_exclude_q=""
if [ -n "$session_id" ]; then
safe_sid=$(printf '%s' "$session_id" | tr -c 'A-Za-z0-9._-' '_')
idfile="$state_dir/${safe_sid}.ids"
syncfile="$state_dir/${safe_sid}.sync.ids"
derivefile="$state_dir/${safe_sid}.derive.ids"
rulefile="$state_dir/${safe_sid}.rules.ids"
if [ -f "$idfile" ]; then
seen=$(tr '\n' ',' < "$idfile" 2>/dev/null | sed 's/,$//')
[ -n "$seen" ] && exclude_q="&exclude_ids=${seen}"
@@ -197,6 +204,10 @@ if [ -n "$session_id" ]; then
derive_seen=$(tr '\n' ',' < "$derivefile" 2>/dev/null | sed 's/,$//' | jq -sRr '@uri' 2>/dev/null) || derive_seen=""
[ -n "$derive_seen" ] && derive_exclude_q="&exclude_derive=${derive_seen}"
fi
if [ -f "$rulefile" ]; then
rule_seen=$(tr '\n' ',' < "$rulefile" 2>/dev/null | sed 's/,$//')
[ -n "$rule_seen" ] && rule_exclude_q="&exclude_rule_ids=${rule_seen}"
fi
fi
# Not `|| exit 0`: an unreachable instance must not discard a local finding
@@ -206,7 +217,7 @@ fi
reached=1
body=$(curl -fsS --max-time 5 \
-H "Authorization: Bearer ${token}" \
"${url%/}/api/plugin/prior-art?path=${path_enc}&code=${code_enc}${repo_q}${exclude_q}${sync_exclude_q}${derive_exclude_q}${shapes_q}" 2>/dev/null) || { body=""; reached=0; }
"${url%/}/api/plugin/prior-art?path=${path_enc}&code=${code_enc}${repo_q}${exclude_q}${sync_exclude_q}${derive_exclude_q}${rule_exclude_q}${shapes_q}" 2>/dev/null) || { body=""; reached=0; }
unreached_context=""
if [ "$reached" = 1 ]; then
scribe_reached "$state_dir" "${safe_sid:-nosession}"
@@ -227,6 +238,9 @@ if [ -n "$body" ]; then
if [ -n "$syncfile" ]; then
printf '%s' "$body" | jq -r '(.sync_note_ids // [])[]?' 2>/dev/null >> "$syncfile" || true
fi
if [ -n "$rulefile" ]; then
printf '%s' "$body" | jq -r '(.rule_ids // [])[]?' 2>/dev/null >> "$rulefile" || true
fi
if [ -n "$derivefile" ]; then
printf '%s' "$body" | jq -r '(.derive_keys // [])[]?' 2>/dev/null >> "$derivefile" || true
fi
+9 -1
View File
@@ -30,6 +30,7 @@ from scribe.routes.design_systems import design_systems_bp
from scribe.routes.trash import trash_bp
from scribe.routes.dashboard import dashboard_bp
from scribe.routes.systems import systems_bp
from scribe.routes.canonical_systems import canonical_systems_bp
from scribe.routes.snippets import snippets_bp
from scribe.routes.webhooks import webhooks_bp
from scribe.mcp import mount_mcp
@@ -95,6 +96,7 @@ def create_app() -> Quart:
app.register_blueprint(trash_bp)
app.register_blueprint(dashboard_bp)
app.register_blueprint(systems_bp)
app.register_blueprint(canonical_systems_bp)
app.register_blueprint(snippets_bp)
app.register_blueprint(webhooks_bp)
@@ -159,7 +161,7 @@ def create_app() -> Quart:
import asyncio
from scribe.services.auth import start_auth_token_retention_loop
from scribe.services.embeddings import backfill_note_embeddings
from scribe.services.embeddings import backfill_note_embeddings, backfill_rule_embeddings
from scribe.services.logging import start_log_retention_loop
from scribe.services.notifications import start_notification_loop
@@ -174,6 +176,12 @@ def create_app() -> Quart:
await backfill_note_embeddings()
except Exception:
logger.warning("Embedding backfill failed", exc_info=True)
# Rules got vectors in milestone 307; every rule written before it
# has none, so this is the pass that makes them findable at all.
try:
await backfill_rule_embeddings()
except Exception:
logger.warning("Rule embedding backfill failed", exc_info=True)
# Snippets written before migration 0070 have no `notes.data` mirror,
# and the location reverse lookup queries that column — an unfilled
# row would read as "no snippet here" rather than as a gap. Separate
+3
View File
@@ -91,6 +91,9 @@ _READ_ONLY_TOOLS = frozenset({
"list_rules", "list_tags", "list_tasks", "list_topics", "list_trash",
"list_always_on_rules", "search",
"get_system", "list_systems", "list_system_records",
# The global area catalog and its mapping REPORT — propose writes nothing;
# map_system_to_canonical is the separate, explicitly-called write.
"list_canonical_systems", "propose_canonical_mappings",
# Reports on the corpus. Reads only — the merge or supersession each
# suggests is a separate, explicitly-called write.
"find_duplicate_snippets", "find_duplicate_records",
+141 -17
View File
@@ -1,7 +1,12 @@
"""MCP tools for the Scribe Rulebook system.
Sixteen tools: rulebook/topic/rule CRUD + subscription management. Thin
wrappers over services/rulebooks.py — ownership is enforced in the service.
Rulebook / topic / rule CRUD, subscription management, and the rule-to-rule
edges. Thin wrappers over services/rulebooks.py — ownership is enforced in the
service, and the record shape comes from rule_brief / rule_detail there rather
than being rebuilt here.
(The header used to say "Sixteen tools" and had been wrong for two milestones;
the count lives in the registration test, which fails when it drifts.)
Destructive ops (delete_*) require confirmed=True; otherwise return a
preview-style warning. Mirrors the pattern in delete_event and the design
@@ -195,8 +200,12 @@ async def delete_topic(topic_id: int, confirmed: bool = False) -> dict:
def _rule_summary(r) -> dict:
"""The list-row shape for a rule: what an agent needs to APPLY it. The
full record (why, how_to_apply, timestamps) is get_rule's job."""
return {"id": r.id, "title": r.title, "statement": r.statement, "topic_id": r.topic_id}
full record (why, how_to_apply, timestamps) is get_rule's job.
One line, because the shape itself lives in the service — this was one of
three hand-written copies that had already drifted apart (note 3026).
"""
return rulebooks_svc.rule_brief(r)
async def list_rules(
@@ -227,6 +236,13 @@ async def list_always_on_rules(project_id: int = 0) -> dict:
Call this at session start. Treat the returned rules as binding for the
session — they apply regardless of which project (if any) is in scope.
Returns the ALWAYS-ON tier only (milestone 307). A `conditional` rule is
still binding when it applies; it just is not resident — it reaches a
session through enter_project (when the project works in an area the rule
is tagged to) or through search(content_type="rule"). Nothing here is a
behaviour change until rules are actually re-tiered: `tier` defaults to
always_on, so an existing rulebook returns exactly what it always did.
Pair with get_project(id).applicable_rules when working on a specific
project to also load that project's subscription-derived rules.
@@ -242,18 +258,25 @@ async def list_always_on_rules(project_id: int = 0) -> dict:
async def get_rule(rule_id: int) -> dict:
"""Fetch a rule by id — full statement + why + how_to_apply."""
"""Fetch a rule by id — full statement + why + how_to_apply.
Also carries what a listing leaves out: the global `systems` this rule is
about, and its `relations`. Read the relations before acting on the rule —
a rule with a `co_surfaces` edge is half of a shape, and an `overrides`
edge means one of the pair is not in force here.
"""
uid = current_user_id()
rule = await rulebooks_svc.get_rule(rule_id, uid)
if rule is None:
raise ValueError(f"rule {rule_id} not found")
return rule.to_dict()
return await rulebooks_svc.rule_detail(uid, rule)
async def create_rule(
topic_id: int, title: str, statement: str,
topic_id: int, title: str, statement: str, when_to_apply: str = "",
why: str = "", how_to_apply: str = "", order_index: int = 0,
force: bool = False,
tier: str = "always_on", system_ids: list[int] | None = None,
arose_from_id: int = 0, force: bool = False,
) -> dict:
"""Create a new rule in a rulebook (a SHARED rule — keep it general).
@@ -273,10 +296,36 @@ async def create_rule(
Reusable code is a SNIPPET. Reach for a rule only when the thing genuinely
is a standing instruction about how to work and nothing else can hold it.
ONE RULE = ONE THING YOU COULD VIOLATE. If a clause can be broken on its
own, and fixing that breakage doesn't require the neighbouring clauses, it
is a separate rule. Rules that FAIL TOGETHER get linked with relate_rules
(kind="co_surfaces"), never merged into one row: a merged rule cannot be
cited, surfaced or suppressed a clause at a time, and it grows without
limit because adding to it is always cheaper than adding a rule.
Args:
topic_id: The topic to attach the rule to.
title: A short imperative title (e.g. "dev is home").
statement: The actionable instruction (required). 1-2 sentences.
when_to_apply: WHEN this rule fires — the trigger, not the
instruction. State the moment or the material: "before any git
push", "when adding a value to a CHECK-gated column", "when a
release is being cut". Write it even though the parameter is
optional: it decides the tier below, it is how the rule is found
when it matters, and a rule nobody can place is a rule nobody
applies.
tier: "always_on" (default) or "conditional".
The test: can you name the trigger WITHOUT naming a system, an
artifact type or a moment? If the honest answer is "whenever you
are working", it is always_on. If you had to name something, it is
conditional — and conditional costs nothing when it is irrelevant,
which is what lets it be as long as it needs to be.
system_ids: Ids from list_canonical_systems — the global AREAS this
rule is about. This is what lets a rule reach a project that is
working in that area, so a CI rule surfaces on a CI change.
arose_from_id: The note or task that CAUSED this rule (an incident, a
decision). Prefer this over naming the record inside `why`, which
cannot be followed and does not survive a rewording.
why: Optional rationale — the reason the rule exists.
how_to_apply: Optional operationalization — when / where it kicks in.
order_index: Display order within the topic (default 0).
@@ -291,16 +340,18 @@ async def create_rule(
return dedup_svc.duplicate_response(dup, "rule")
rule = await rulebooks_svc.create_rule(
topic_id=topic_id, user_id=uid,
title=title, statement=statement,
title=title, statement=statement, when_to_apply=when_to_apply,
tier=tier, arose_from_id=arose_from_id,
why=why, how_to_apply=how_to_apply, order_index=order_index,
)
return rule.to_dict()
return await rulebooks_svc.rule_detail(uid, rule, system_ids)
async def create_project_rule(
project_id: int, statement: str, title: str = "",
project_id: int, statement: str, title: str = "", when_to_apply: str = "",
why: str = "", how_to_apply: str = "", order_index: int = 0,
force: bool = False,
tier: str = "always_on", system_ids: list[int] | None = None,
arose_from_id: int = 0, force: bool = False,
) -> dict:
"""Create a rule scoped to a single project (no rulebook needed).
@@ -312,11 +363,24 @@ async def create_project_rule(
the rule is returned in get_project's applicable_rules (under
project_rules) and in list_rules(project_id=...).
ONE RULE = ONE THING YOU COULD VIOLATE — see create_rule. A rule that
STRICTENS or REPLACES an inherited one is not a fresh rule: write it, then
relate_rules(kind="overrides") to the rule it supersedes, so the pair stays
connected instead of drifting into a contradiction nobody notices. A rule
that merely adds local detail to an inherited one uses "elaborates".
Args:
project_id: The project to attach the rule to.
statement: The actionable instruction (required). 1-2 sentences.
title: Short imperative title. If empty, derived from the first ~50
characters of statement.
when_to_apply: WHEN this rule fires — the trigger, not the
instruction. See create_rule; it decides the tier and it is how
the rule is found at the moment it matters.
tier: "always_on" (default) or "conditional" — see create_rule.
system_ids: Ids from list_canonical_systems — the global AREAS this
rule is about.
arose_from_id: The note or task that CAUSED this rule.
why: Optional rationale — the reason the rule exists.
how_to_apply: Optional operationalization — when / where it kicks in.
order_index: Display order within the project's rule list (default 0).
@@ -332,23 +396,36 @@ async def create_project_rule(
return dedup_svc.duplicate_response(dup, "rule")
rule = await rulebooks_svc.create_project_rule(
project_id=project_id, user_id=uid,
title=derived_title, statement=statement,
title=derived_title, statement=statement, when_to_apply=when_to_apply,
tier=tier, arose_from_id=arose_from_id,
why=why, how_to_apply=how_to_apply, order_index=order_index,
)
return rule.to_dict()
return await rulebooks_svc.rule_detail(uid, rule, system_ids)
async def update_rule(
rule_id: int, title: str = "", statement: str = "",
rule_id: int, title: str = "", statement: str = "", when_to_apply: str = "",
why: str = "", how_to_apply: str = "", order_index: int = -1,
tier: str = "", system_ids: list[int] | None = None, arose_from_id: int = 0,
) -> dict:
"""Update a rule. Empty strings / order_index=-1 leave fields unchanged."""
"""Update a rule. Empty strings / order_index=-1 leave fields unchanged.
Adding `when_to_apply` and a `tier` to an existing rule is the ordinary way
a rule stops being preloaded into every session and starts arriving when it
is relevant. `system_ids` REPLACES the rule's areas (pass [] to clear).
"""
uid = current_user_id()
fields: dict = {}
if title:
fields["title"] = title
if statement:
fields["statement"] = statement
if when_to_apply:
fields["when_to_apply"] = when_to_apply
if tier:
fields["tier"] = tier
if arose_from_id:
fields["arose_from_id"] = arose_from_id
if why:
fields["why"] = why
if how_to_apply:
@@ -358,7 +435,7 @@ async def update_rule(
rule = await rulebooks_svc.update_rule(rule_id, uid, **fields)
if rule is None:
raise ValueError(f"rule {rule_id} not found")
return rule.to_dict()
return await rulebooks_svc.rule_detail(uid, rule, system_ids)
async def delete_rule(rule_id: int, confirmed: bool = False) -> dict:
@@ -496,12 +573,59 @@ async def unsuppress_topic_for_project(
return {"project_id": project_id, "topic_id": topic_id, "suppressed": False}
async def relate_rules(
from_rule_id: int, to_rule_id: int, kind: str, note: str = "",
) -> dict:
"""Draw a typed edge between two rules. Both must be yours.
Reach for this INSTEAD of merging or duplicating:
- kind="co_surfaces" — these two fail together, so they must arrive
together. Use it when you are tempted to fold one rule into another
because "either could surface without the other": that instinct is
right and merging is the wrong fix, because a merged rule cannot be
cited, suppressed or surfaced a clause at a time. Symmetric — draw it
once, it reads from both ends.
- kind="overrides" — this rule supersedes that one for its scope. Use it
when a project rule is stricter than, or replaces, an inherited one,
instead of writing a near-copy that will drift from its parent.
- kind="elaborates" — this rule adds local specifics to that one, and
should arrive with it rather than instead of it.
Idempotent: re-drawing an existing edge returns it.
Args:
note: WHY the edge holds. Worth writing for the same reason a rule
carries `why` — a later reader deciding whether it still applies
needs the reasoning, not just the fact.
"""
uid = current_user_id()
relation = await rulebooks_svc.add_rule_relation(
uid, from_rule_id, to_rule_id, kind, note,
)
if relation is None:
raise ValueError(
f"rule {from_rule_id} or {to_rule_id} not found (both must be yours)"
)
return relation.to_dict()
async def unrelate_rules(relation_id: int) -> dict:
"""Remove one edge between rules (from relate_rules / get_rule.relations)."""
uid = current_user_id()
if not await rulebooks_svc.remove_rule_relation(uid, relation_id):
raise ValueError(f"relation {relation_id} not found")
return {"deleted": relation_id}
def register(mcp) -> None:
for fn in (
list_rulebooks, get_rulebook, create_rulebook, update_rulebook, delete_rulebook,
list_topics, create_topic, update_topic, delete_topic,
list_rules, list_always_on_rules, get_rule,
create_rule, create_project_rule, update_rule, delete_rule,
relate_rules, unrelate_rules,
subscribe_project_to_rulebook, unsubscribe_project_from_rulebook,
suppress_rule_for_project, unsuppress_rule_for_project,
suppress_topic_for_project, unsuppress_topic_for_project,
+44 -2
View File
@@ -11,10 +11,44 @@ import time
from scribe.mcp._context import current_user_id
from scribe.services.access import owner_names_for
from scribe.services.embeddings import DEFAULT_SIMILARITY_THRESHOLD, semantic_search_notes
from scribe.services.embeddings import (
DEFAULT_SIMILARITY_THRESHOLD, semantic_search_notes, semantic_search_rules,
)
from scribe.services.retrieval_telemetry import record_retrieval, retrieval_summary
async def _search_rules(uid: int, q: str, limit: int) -> dict:
"""Rules by meaning — a separate result shape because a rule IS different.
A rule hit carries `why` and `how_to_apply`: they are the operational half
of a rule and the session-start payload never includes them, so a caller
who went looking should get the whole thing rather than a summary they then
have to re-fetch.
Rules are not project-scoped the way notes are (a family rule belongs to no
project), so `project_id` and `system_id` do not apply here.
"""
raw = await semantic_search_rules(uid, q, limit=limit)
return {
"results": [
{
"id": rule.id,
"title": rule.title,
"statement": rule.statement,
"when_to_apply": rule.when_to_apply or "",
"tier": rule.tier,
"why": rule.why or "",
"how_to_apply": rule.how_to_apply or "",
"topic_id": rule.topic_id,
"project_id": rule.project_id,
"similarity": float(score),
}
for score, rule in raw
],
"total": len(raw),
}
async def search(
q: str,
content_type: str = "all",
@@ -33,7 +67,13 @@ async def search(
Args:
q: search query string.
content_type: 'all' (default), 'note' (notes only), or 'task' (tasks only).
content_type: 'all' (default), 'note' (notes only), 'task' (tasks
only), or 'rule' (RULES only — the operator's standing
instructions, searchable by meaning since milestone 307).
Reach for 'rule' when you want to know whether a standing
instruction covers something: "is there a rule about release
tagging?". A hit carries the rule's `why` and `how_to_apply`,
which the session-start payload does not.
limit: maximum number of results (1-50).
project_id: Scope results to one project. PASS THE ACTIVE PROJECT'S ID
whenever a project is in scope (the one you entered with
@@ -56,6 +96,8 @@ async def search(
"""
uid = current_user_id()
limit = max(1, min(limit, 50))
if content_type == "rule":
return await _search_rules(uid, q, limit)
is_task = {"note": False, "task": True}.get(content_type) # None => any
t0 = time.perf_counter()
raw = await semantic_search_notes(
+124 -30
View File
@@ -13,6 +13,7 @@ Sentinels (match the milestone/task tool conventions):
from __future__ import annotations
from scribe.mcp._context import current_user_id
from scribe.services import canonical_systems as canonical_systems_svc
from scribe.services import notes as notes_svc
from scribe.services import systems as systems_svc
@@ -30,10 +31,9 @@ _BOOTSTRAP_TITLES = 6
# design (rule #115): archetypes any codebase could have, never one
# install's subsystems. Mint freely beyond the list; the duplicate gate
# guards sprawl.
# The standard vocabulary lives with the service (services/systems.
# STANDARD_SYSTEMS) since milestone 297 — the inception seed mints it and this
# ask names it, one list for both.
_STANDARD_SYSTEMS = tuple(name for name, _charter in systems_svc.STANDARD_SYSTEMS)
# The standard vocabulary lives in the GLOBAL canonical catalog since
# milestone 307 — the inception seed mints it and this ask names it, one list
# for both, now a table so a rule can reference an area by id (note 3026).
async def bootstrap_systems_ask(user_id: int, project_id: int) -> str | None:
@@ -67,6 +67,17 @@ async def bootstrap_systems_ask(user_id: int, project_id: int) -> str | None:
titles = "; ".join(
'"' + " ".join((n.title or "").split())[:70] + '"' for n in recent
)
try:
standard = ", ".join(name for name, _charter in await systems_svc.standard_systems())
except Exception:
standard = ""
# An install whose catalog is empty still gets a usable ask — the standard
# names are an aid, not the point of the question.
standard_line = (
"Where an area fits a standard name, use it verbatim so it means the "
f"same thing in every project: {standard}. Mint freely beyond that "
"list — the duplicate gate guards sprawl. "
) if standard else "The duplicate gate guards sprawl. "
return (
f"This project has {total} records and NO Systems modelled — none of "
"them can be tagged to an area, so recurring problem-spots stay "
@@ -74,10 +85,8 @@ async def bootstrap_systems_ask(user_id: int, project_id: int) -> str | None:
"asking permission — creating Systems is your call, not an approval "
f"flow. From the areas the records themselves name (recent: {titles}), "
"create_system 3-6 Systems, each with a one-paragraph charter, then "
"tag this record (system_ids=[...]). Where an area fits a standard "
f"name, use it verbatim so it means the same thing in every project: "
f"{', '.join(_STANDARD_SYSTEMS)}. Mint freely beyond that list — the "
"duplicate gate guards sprawl. This ask repeats until the first "
f"tag this record (system_ids=[...]). {standard_line}"
"This ask repeats until the first "
"System exists; answering it once retires it for every future record."
)
@@ -188,36 +197,60 @@ async def create_system(
normalized name already exists in this project (archived included), the
call returns {"duplicate": true, "existing_id": ...} instead of creating —
tag records to that one, or update_system it if its charter needs work.
Also mapped against the GLOBAL area catalog, so the same word means the
same thing in every project (milestone 307). A name that IS a catalog area
up to spelling ("CI and Release" vs "CI & Release") is mapped for you and
the response says so. A name that merely RESEMBLES one comes back with
`canonical_suggestion` — an offer, not a decision: apply it with
map_system_to_canonical if it really is that area, ignore it if this is a
project-specific area. Either way the System is created; the catalog never
blocks a name.
"""
uid = current_user_id()
norm = " ".join(name.split()).lower()
if norm:
try:
existing = await systems_svc.list_systems(
uid, project_id, include_archived=True
)
except Exception:
existing = []
for s in existing:
if " ".join(s.name.split()).lower() == norm:
return {
"duplicate": True,
"existing_id": s.id,
"message": (
f"System '{s.name}' (#{s.id}) already covers this area "
"in this project. Tag records to it with system_ids, "
"or update_system it if the charter needs revising — "
"a second System with the same name would split the "
"area's records across two piles."
),
}
assessment = await systems_svc.assess_system_name(uid, project_id, name)
duplicate = assessment["duplicate"]
if duplicate:
return {
"duplicate": True,
"existing_id": duplicate["id"],
"message": (
f"System '{duplicate['name']}' (#{duplicate['id']}) already "
"covers this area in this project. Tag records to it with "
"system_ids, or update_system it if the charter needs "
"revising — a second System with the same name would split "
"the area's records across two piles."
),
}
# An exact match is mechanical, so it is applied; an overlap is a judgment
# call, so it is only offered (see services/canonical_systems).
canonical = assessment["canonical"]
applied = canonical["id"] if canonical and canonical["basis"] == "exact" else None
system = await systems_svc.create_system(
uid, project_id=project_id, name=name,
description=description or None, color=color or None,
canonical_id=applied,
)
if system is None:
raise ValueError(f"cannot create system in project {project_id} (no write access)")
return system.to_dict()
out = system.to_dict()
if applied:
out["canonical_note"] = (
f"Mapped to the global area '{canonical['name']}' — the same "
"spelling-insensitive name. Your System keeps the name you gave it."
)
elif canonical:
out["canonical_suggestion"] = {
**canonical,
"message": (
f"The global catalog has '{canonical['name']}', which may be "
f"this same area. If it is, map_system_to_canonical("
f"{system.id}, {canonical['id']}) so records and rules about "
"this area line up across projects. If this area is specific "
"to this project, ignore it — unmapped is a valid state."
),
}
return out
async def list_systems(project_id: int, include_archived: bool = False) -> dict:
@@ -322,6 +355,64 @@ async def delete_system(system_id: int) -> dict:
return {"message": f"System {system_id} deleted."}
async def list_canonical_systems() -> dict:
"""The GLOBAL vocabulary of area names, shared by every project.
These are the standard names to prefer when creating a System, so the same
word means the same thing in every project on the instance — and, from
milestone 307, the ids a cross-project record can point at. A project's own
System keeps whatever name the project calls the area; mapping it here is
an association, never a rename.
Reach for it before create_system when the area is an ordinary one (CI,
auth, storage, the API, the UI), and pass the matching `canonical_id`.
"""
entries = await canonical_systems_svc.list_canonical_systems()
return {"canonical_systems": [e.to_dict() for e in entries]}
async def propose_canonical_mappings(project_id: int) -> dict:
"""Suggest a global area for each of this project's UNMAPPED Systems.
Returns PROPOSALS ONLY — nothing is written. Confirm the ones that are
right with map_system_to_canonical(system_id, canonical_id); ignore the
rest. Each carries a `basis`:
- `exact` — the names reduce to the same match key ("CI and Release" vs
"CI & Release"). Safe to confirm without much thought.
- `overlap` — they share a meaningful word ("CI & runners" vs "CI &
Release"). A judgment call: confirm only if they really are the same
area, since a wrong mapping surfaces cross-project records in the wrong
place.
A System with no proposal is not a problem — unmapped is a valid resting
state, and a genuinely project-specific area should stay that way.
"""
uid = current_user_id()
return {"proposals": await canonical_systems_svc.propose_mappings(uid, project_id)}
async def map_system_to_canonical(system_id: int, canonical_id: int = 0) -> dict:
"""Map one of a project's Systems onto a global area (or clear it).
Sets `canonical_id` and NOTHING else — the System's name, charter and every
record tagged to it are untouched. Pass canonical_id=0 to unmap.
Args:
canonical_id: id from list_canonical_systems; 0 clears the mapping.
"""
uid = current_user_id()
system = await canonical_systems_svc.set_system_canonical(
uid, system_id, canonical_id or None,
)
if system is None:
raise ValueError(
f"system {system_id} not found, no write access, "
f"or canonical_id {canonical_id} is not a live catalog entry"
)
return system.to_dict()
def register(mcp) -> None:
for fn in (
create_system,
@@ -330,5 +421,8 @@ def register(mcp) -> None:
update_system,
list_system_records,
delete_system,
list_canonical_systems,
propose_canonical_mappings,
map_system_to_canonical,
):
mcp.tool(name=fn.__name__)(fn)
+5 -2
View File
@@ -25,7 +25,7 @@ from scribe.models.user import User # noqa: E402, F401
from scribe.models.app_log import AppLog # noqa: E402, F401
from scribe.models.password_reset import PasswordResetToken # noqa: E402, F401
from scribe.models.invitation import InvitationToken # noqa: E402, F401
from scribe.models.embedding import NoteEmbedding # noqa: E402, F401
from scribe.models.embedding import NoteEmbedding, RuleEmbedding # noqa: E402, F401
from scribe.models.retrieval_log import RetrievalLog # noqa: E402, F401
from scribe.models.note_usage import NoteUsageEvent # noqa: E402, F401
from scribe.models.project import Project # noqa: E402, F401
@@ -39,8 +39,11 @@ from scribe.models.share import NoteShare, ProjectShare # noqa: E402, F401
from scribe.models.notification import Notification # noqa: E402, F401
from scribe.models.api_key import ApiKey # noqa: E402, F401
from scribe.models.user_profile import UserProfile # noqa: E402, F401
# Imported before rulebook: rule_systems foreign-keys canonical_systems.
from scribe.models.canonical_system import CanonicalSystem # noqa: E402, F401
from scribe.models.rulebook import ( # noqa: E402, F401
Rulebook, RulebookTopic, Rule, project_rulebook_subscriptions,
Rulebook, RulebookTopic, Rule, RuleRelation, project_rulebook_subscriptions,
rule_systems,
)
from scribe.models.repo_binding import RepoBinding # noqa: E402, F401
from scribe.models.forge_connection import ForgeConnection # noqa: E402, F401
+58
View File
@@ -0,0 +1,58 @@
from sqlalchemy import Index, Integer, Text, text
from sqlalchemy.orm import Mapped, mapped_column
from scribe.models import Base
from scribe.models.base import SoftDeleteMixin, TimestampMixin, iso
class CanonicalSystem(Base, TimestampMixin, SoftDeleteMixin):
"""A GLOBAL area name — the shared vocabulary every project's Systems
can point at (milestone 307, decision note 3026).
A `System` is per-project and NOT NULL on project_id, so nothing outside a
project can reference one: a rule that applies across projects has no way
to say "this is about CI" without chaining itself to one project's row.
This table is that join key. It carries no `user_id` on purpose — a shared
project must INHERIT the vocabulary rather than re-earn it, so the catalog
is global and the same word means the same thing in every install.
It is a convergence aid, never a gate: `systems.canonical_id` is nullable,
an unmapped System stays fully usable, and `record_systems` never sees this
table at all — the local name is a legitimate local label and is never
rewritten to match.
`slug` is the match key, not a display value. It folds the spelling
differences that produced four names for one area on the author's own
instance ("CI & Release" / "CI and Release" / "CI & release"): an exact slug
hit maps automatically, and anything short of that becomes a proposal for a
human to confirm. See services/canonical_systems.canonical_slug.
"""
__tablename__ = "canonical_systems"
id: Mapped[int] = mapped_column(primary_key=True)
name: Mapped[str] = mapped_column(Text, nullable=False)
# Normalized match key — unique among LIVE rows, so a soft-deleted entry
# doesn't block recreating the same area (the partial-unique convention
# rules/topics already use).
slug: Mapped[str] = mapped_column(Text, nullable=False)
description: Mapped[str | None] = mapped_column(Text, nullable=True)
order_index: Mapped[int] = mapped_column(Integer, default=0, server_default="0")
__table_args__ = (
Index(
"uq_canonical_systems_slug", "slug",
unique=True, postgresql_where=text("deleted_at IS NULL"),
),
)
def to_dict(self) -> dict:
return {
"id": self.id,
"name": self.name,
"slug": self.slug,
"description": self.description,
"order_index": self.order_index,
"created_at": iso(self.created_at),
"updated_at": iso(self.updated_at),
}
+47 -1
View File
@@ -1,7 +1,7 @@
from datetime import datetime, timezone
from pgvector.sqlalchemy import Vector
from sqlalchemy import DateTime, ForeignKey, Integer, Text
from sqlalchemy import BigInteger, DateTime, ForeignKey, Integer, Text
from sqlalchemy.orm import Mapped, mapped_column
from scribe.models import Base
@@ -45,3 +45,49 @@ class NoteEmbedding(Base):
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
)
class RuleEmbedding(Base):
"""One embedding vector per CHUNK of a rule (milestone 307, note 3026).
A SIBLING of NoteEmbedding rather than a generalisation of it, decided
deliberately:
- The embedding ROW could have been made polymorphic. The SEARCH could not.
`semantic_search_notes` is a long function of Note-specific scoping —
the visibility clause, the supersession penalty, note_type/task_kind and
system filters — and a rule shares none of it. Rules scope by rulebook
ownership and project applicability instead.
- Generalising the row while still needing two searches is the worst of
both: a polymorphic key with referential integrity to neither table, on
the path every session start runs, to share four columns.
- What is genuinely common is BEHAVIOUR, not storage — get_embedding,
chunk_document, embedding_text and CHUNKER_VERSION are already free
functions and are reused as-is. Sharing those is the DRY win; sharing
the table would have been the DRY costume.
No `user_id`: NoteEmbedding carries one and its own search deliberately
ignores it (scoping on the note instead, or shared records become
unreachable). Rather than repeat a column that exists to be ignored, a
rule's reach is resolved by joining the rule.
"""
__tablename__ = "rule_embeddings"
rule_id: Mapped[int] = mapped_column(
BigInteger,
ForeignKey("rules.id", ondelete="CASCADE"),
primary_key=True,
)
chunk_index: Mapped[int] = mapped_column(Integer, primary_key=True)
embedding: Mapped[list] = mapped_column(Vector(EMBEDDING_DIM), nullable=False)
# Exactly what this vector encodes — inspectable when a ranking surprises.
# For a rule this is the trigger-first document, NOT the rule's `why`:
# `why` is dated incident narrative and would drag every rule toward one
# centroid (measured in note 2485).
chunk_text: Mapped[str] = mapped_column(Text, nullable=False)
chunker_version: Mapped[int] = mapped_column(Integer, nullable=False)
updated_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
)
+87 -2
View File
@@ -1,10 +1,13 @@
from datetime import datetime, timezone
from sqlalchemy import BigInteger, Boolean, Column, DateTime, ForeignKey, Index, Integer, Table, Text, text
from sqlalchemy import (
BigInteger, Boolean, Column, DateTime, ForeignKey, Index, Integer, Table,
Text, UniqueConstraint, text,
)
from sqlalchemy.orm import Mapped, mapped_column
from scribe.models import Base
from scribe.models.base import SoftDeleteMixin, TimestampMixin, iso
from scribe.models.base import CreatedAtMixin, SoftDeleteMixin, TimestampMixin, iso
class Rulebook(Base, TimestampMixin, SoftDeleteMixin):
@@ -90,8 +93,26 @@ class Rule(Base, TimestampMixin, SoftDeleteMixin):
)
title: Mapped[str] = mapped_column(Text)
statement: Mapped[str] = mapped_column(Text)
# WHEN this rule applies — the trigger, not the instruction. Required of
# new rules at the service layer and nullable here, because rules written
# before migration 0088 have none and a migration cannot invent one.
# It carries three jobs at once (note 3026): it is the tier test made
# concrete, the readable form of the canon tag, and the half of the
# document that makes a rule findable by meaning.
when_to_apply: Mapped[str | None] = mapped_column(Text, nullable=True)
# always_on = preloaded into every session, as every rule is today.
# conditional = reachable, and surfaced when its trigger fires. The
# default preserves existing behaviour exactly: nothing stops binding
# because of an upgrade. CHECK ck_rules_tier (migration 0088, rule 36).
tier: Mapped[str] = mapped_column(Text, default="always_on", server_default="always_on")
why: Mapped[str | None] = mapped_column(Text, nullable=True)
how_to_apply: Mapped[str | None] = mapped_column(Text, nullable=True)
# The record that caused this rule — the edge notes and tasks already
# have. Rule 46's `why` names note 2813 in prose; this is that link as a
# field, so it survives a rewording of the paragraph.
arose_from_id: Mapped[int | None] = mapped_column(
BigInteger, ForeignKey("notes.id", ondelete="SET NULL"), nullable=True
)
order_index: Mapped[int] = mapped_column(Integer, default=0)
def to_dict(self) -> dict:
@@ -101,14 +122,78 @@ class Rule(Base, TimestampMixin, SoftDeleteMixin):
"project_id": self.project_id,
"title": self.title,
"statement": self.statement,
"when_to_apply": self.when_to_apply or "",
"tier": self.tier,
"why": self.why or "",
"how_to_apply": self.how_to_apply or "",
"arose_from_id": self.arose_from_id,
"order_index": self.order_index,
"created_at": iso(self.created_at),
"updated_at": iso(self.updated_at),
}
# Which global AREA a rule is about (milestone 307). Points at the canonical
# catalog, NEVER at a project's `systems` row: a rule that spans projects
# cannot be chained to one project's vocabulary. This is the edge three
# projects were drawing by hand, as rule text copied into a System's charter.
rule_systems = Table(
"rule_systems",
Base.metadata,
Column("rule_id", BigInteger, ForeignKey("rules.id", ondelete="CASCADE"), primary_key=True),
Column("canonical_id", Integer, ForeignKey("canonical_systems.id", ondelete="CASCADE"), primary_key=True),
Column("created_at", DateTime(timezone=True), default=lambda: datetime.now(timezone.utc)),
)
class RuleRelation(Base, CreatedAtMixin):
"""A typed edge between two rules. Each kind exists because its ABSENCE
forced a workaround somewhere in the operator's rulebook (note 3026).
- ``co_surfaces`` — these fail together, so they must arrive together.
Without it, the only way to guarantee that was to merge them into one
row, which is what happened to rule 46: split into 144, folded back the
same day because "either rule could surface without the other."
Symmetric in meaning; stored once and read both ways.
- ``overrides`` — this rule supersedes that one for its scope. Only
*suppression* existed, so an override had to be written as a parallel
rule that then drifts from its parent.
- ``elaborates`` — this rule adds local specifics to that one; surfacing
the parent brings the addendum with it.
``note`` records WHY the edge was drawn, for the same reason a rule
carries `why`: a later reader deciding whether it still holds needs the
reasoning, not just the fact.
"""
__tablename__ = "rule_relations"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
from_rule_id: Mapped[int] = mapped_column(
BigInteger, ForeignKey("rules.id", ondelete="CASCADE"), index=True
)
to_rule_id: Mapped[int] = mapped_column(
BigInteger, ForeignKey("rules.id", ondelete="CASCADE"), index=True
)
# CHECK ck_rule_relations_kind (migration 0088, rule 36).
kind: Mapped[str] = mapped_column(Text)
note: Mapped[str | None] = mapped_column(Text, nullable=True)
__table_args__ = (
UniqueConstraint("from_rule_id", "to_rule_id", "kind", name="uq_rule_relations_edge"),
)
def to_dict(self) -> dict:
return {
"id": self.id,
"from_rule_id": self.from_rule_id,
"to_rule_id": self.to_rule_id,
"kind": self.kind,
"note": self.note or "",
"created_at": iso(self.created_at),
}
# Pure many-to-many — no model class, just the join table.
project_rulebook_subscriptions = Table(
"project_rulebook_subscriptions",
+10
View File
@@ -24,6 +24,15 @@ class System(Base, TimestampMixin, SoftDeleteMixin):
Integer, ForeignKey("projects.id", ondelete="CASCADE")
)
name: Mapped[str] = mapped_column(Text, default="", server_default="")
# The GLOBAL area this local System is an instance of (milestone 307).
# Nullable and SET NULL on purpose: the catalog is a convergence aid, not a
# gate — an unmapped System is fully usable, and retiring a canonical entry
# must never take a project's System with it. The local `name` is NEVER
# rewritten to match the canonical one; this column is the join key, and
# the name stays whatever the project calls the area.
canonical_id: Mapped[int | None] = mapped_column(
Integer, ForeignKey("canonical_systems.id", ondelete="SET NULL"), nullable=True
)
description: Mapped[str | None] = mapped_column(Text, nullable=True)
color: Mapped[str | None] = mapped_column(Text, nullable=True)
# active | archived — systems accumulate; archive rather than delete.
@@ -40,6 +49,7 @@ class System(Base, TimestampMixin, SoftDeleteMixin):
"user_id": self.user_id,
"project_id": self.project_id,
"name": self.name,
"canonical_id": self.canonical_id,
"description": self.description,
"color": self.color,
"status": self.status,
+93
View File
@@ -0,0 +1,93 @@
"""Canonical-system routes — the GLOBAL area vocabulary, and the mapping of a
project's Systems onto it (milestone 307, decision note 3026).
Two shapes live here because they are two halves of one idea:
- `/api/canonical-systems` — the catalog itself. Readable by any signed-in
user (it is shared vocabulary, not user data); writable only by an admin,
since a global list anyone can extend stops being a shared list.
- the mapping endpoints — authorised by the PROJECT, because mapping writes a
project's own System row. The service enforces both; these are thin wrappers.
"""
import logging
from quart import Blueprint, jsonify, request
from scribe.auth import admin_required, get_current_user_id, login_required
from scribe.routes.utils import not_found
from scribe.services import canonical_systems as canonical_svc
from scribe.services.projects import get_project_for_user
logger = logging.getLogger(__name__)
canonical_systems_bp = Blueprint("canonical_systems", __name__, url_prefix="/api")
@canonical_systems_bp.route("/canonical-systems", methods=["GET"])
@login_required
async def list_canonical_systems_route():
entries = await canonical_svc.list_canonical_systems()
return jsonify({"canonical_systems": [e.to_dict() for e in entries]})
@canonical_systems_bp.route("/canonical-systems", methods=["POST"])
@admin_required
async def create_canonical_system_route():
uid = get_current_user_id()
data = await request.get_json() or {}
if not (data.get("name") or "").strip():
return jsonify({"error": "name is required"}), 400
entry = await canonical_svc.create_canonical_system(
uid, data["name"], description=data.get("description"),
)
if entry is None:
return jsonify({"error": "Permission denied"}), 403
# The slug duplicate gate answers with the entry that already covers the
# area rather than minting a second spelling of it — 409, not a silent
# second row (the whole point of the table).
if isinstance(entry, dict):
return jsonify(entry), 409
return jsonify(entry.to_dict()), 201
@canonical_systems_bp.route("/canonical-systems/<int:canonical_id>", methods=["PATCH"])
@admin_required
async def update_canonical_system_route(canonical_id: int):
uid = get_current_user_id()
data = await request.get_json() or {}
fields = {k: v for k, v in data.items() if k in ("name", "description", "order_index")}
entry = await canonical_svc.update_canonical_system(uid, canonical_id, **fields)
if entry is None:
return not_found("Canonical system")
return jsonify(entry.to_dict())
@canonical_systems_bp.route(
"/projects/<int:project_id>/canonical-proposals", methods=["GET"]
)
@login_required
async def propose_canonical_mappings_route(project_id: int):
"""Proposals only — this endpoint writes nothing. The PUT below applies one."""
uid = get_current_user_id()
if await get_project_for_user(uid, project_id) is None:
return not_found("Project")
return jsonify({"proposals": await canonical_svc.propose_mappings(uid, project_id)})
@canonical_systems_bp.route("/systems/<int:system_id>/canonical", methods=["PUT"])
@login_required
async def map_system_to_canonical_route(system_id: int):
"""Map or unmap one System. Body: {"canonical_id": <id>|null}.
Sets that column and nothing else — no rename, no change to which records
are tagged to the System.
"""
uid = get_current_user_id()
data = await request.get_json() or {}
canonical_id = data.get("canonical_id")
if canonical_id is not None and not isinstance(canonical_id, int):
return jsonify({"error": "canonical_id must be an integer or null"}), 400
system = await canonical_svc.set_system_canonical(uid, system_id, canonical_id)
if system is None:
return not_found("System or canonical system")
return jsonify(system.to_dict())
+7
View File
@@ -129,6 +129,11 @@ async def write_path_prior_art():
surfaced. A separate channel on purpose: a reuse
hint shown early must not suppress the record-sync
nudge when the recorded file is edited later.
exclude_rule_ids (opt) — comma-separated RULE ids already surfaced
this session. Its own channel like the three
above, and for the same reason: a rule named
twenty turns ago should not be re-offered on
every subsequent write.
exclude_derive (opt) — comma-separated derive keys (a derive group id
or `canon:<snippet_id>`) already named this
session by the ledger arm (#2900); its own
@@ -151,6 +156,7 @@ async def write_path_prior_art():
exclude_derive = [
p.strip() for p in (request.args.get("exclude_derive") or "").split(",") if p.strip()
]
exclude_rule_ids = _int_list(request.args.get("exclude_rule_ids"))
shapes = _parse_shapes(request.args.get("shapes") or "")
api_key = getattr(g, "api_key", None)
may_stamp = api_key is None or getattr(api_key, "scope", "") == "write"
@@ -161,6 +167,7 @@ async def write_path_prior_art():
stamp_shapes=shapes if may_stamp else None,
repo_key=repo_bindings_svc.normalize_repo_key(repo) if repo else "",
exclude_derive=exclude_derive,
exclude_rule_ids=exclude_rule_ids,
)
return jsonify(result)
+52 -7
View File
@@ -162,33 +162,73 @@ async def create_rule(topic_id: int):
why=data.get("why", ""),
how_to_apply=data.get("how_to_apply", ""),
order_index=data.get("order_index", 0),
when_to_apply=data.get("when_to_apply", ""),
tier=data.get("tier", "always_on"),
arose_from_id=data.get("arose_from_id", 0) or 0,
)
except ValueError as exc:
return jsonify({"error": str(exc)}), 404
return jsonify(rule.to_dict()), 201
return jsonify(await rulebooks_svc.rule_detail(
get_current_user_id(), rule, data.get("system_ids"),
)), 201
@rulebooks_bp.get("/rules/<int:rule_id>")
@login_required
async def get_rule(rule_id: int):
rule = await rulebooks_svc.get_rule(rule_id, get_current_user_id())
uid = get_current_user_id()
rule = await rulebooks_svc.get_rule(rule_id, uid)
if rule is None:
return jsonify({"error": "rule not found"}), 404
return jsonify(rule.to_dict())
return jsonify(await rulebooks_svc.rule_detail(uid, rule))
@rulebooks_bp.patch("/rules/<int:rule_id>")
@login_required
async def update_rule(rule_id: int):
data = await request.get_json() or {}
uid = get_current_user_id()
fields = {
k: v for k, v in data.items()
if k in ("title", "statement", "why", "how_to_apply", "order_index")
if k in ("title", "statement", "why", "how_to_apply", "order_index",
"when_to_apply", "tier", "arose_from_id")
}
rule = await rulebooks_svc.update_rule(rule_id, get_current_user_id(), **fields)
rule = await rulebooks_svc.update_rule(rule_id, uid, **fields)
if rule is None:
return jsonify({"error": "rule not found"}), 404
return jsonify(rule.to_dict())
return jsonify(await rulebooks_svc.rule_detail(uid, rule, data.get("system_ids")))
@rulebooks_bp.post("/rules/<int:rule_id>/relations")
@login_required
async def relate_rules(rule_id: int):
"""Draw a typed edge FROM this rule to another.
Body: {"to_rule_id": N, "kind": "co_surfaces"|"overrides"|"elaborates",
"note": "..."}. Idempotent — re-drawing an edge returns the existing one.
"""
data = await request.get_json() or {}
to_rule_id = data.get("to_rule_id")
if not isinstance(to_rule_id, int):
return jsonify({"error": "to_rule_id is required"}), 400
try:
relation = await rulebooks_svc.add_rule_relation(
get_current_user_id(), rule_id, to_rule_id,
data.get("kind", ""), data.get("note", ""),
)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
if relation is None:
return jsonify({"error": "rule not found"}), 404
return jsonify(relation.to_dict()), 201
@rulebooks_bp.delete("/rule-relations/<int:relation_id>")
@login_required
async def unrelate_rules(relation_id: int):
if not await rulebooks_svc.remove_rule_relation(get_current_user_id(), relation_id):
return jsonify({"error": "relation not found"}), 404
return "", 204
@rulebooks_bp.delete("/rules/<int:rule_id>")
@@ -332,7 +372,12 @@ async def create_project_rule(project_id: int):
why=data.get("why", ""),
how_to_apply=data.get("how_to_apply", ""),
order_index=data.get("order_index", 0),
when_to_apply=data.get("when_to_apply", ""),
tier=data.get("tier", "always_on"),
arose_from_id=data.get("arose_from_id", 0) or 0,
)
except ValueError as exc:
return jsonify({"error": str(exc)}), 404
return jsonify(rule.to_dict()), 201
return jsonify(await rulebooks_svc.rule_detail(
get_current_user_id(), rule, data.get("system_ids"),
)), 201
+25 -1
View File
@@ -62,14 +62,38 @@ async def create_system_route(project_id: int):
data = await request.get_json() or {}
if not (data.get("name") or "").strip():
return jsonify({"error": "name is required"}), 400
# The same gate the MCP door enforces. It lived only in the tool layer
# until now, which is exactly how the web UI shipped without gates the
# agent surface had (#2482) — one service call, one answer (rule 33).
assessment = await systems_svc.assess_system_name(uid, project_id, data["name"])
duplicate = assessment["duplicate"]
if duplicate and not data.get("force"):
return jsonify({
"duplicate": True,
"existing_id": duplicate["id"],
"error": (
f"{duplicate['name']}” already covers this area in this "
"project. Tag records to it, or rename it if its charter has "
"moved on — a second System with the same name splits the "
"area's records across two piles."
),
}), 409
canonical = assessment["canonical"]
# Exact is mechanical and applied; overlap is a judgment call and is only
# offered back for the form to present.
applied = canonical["id"] if canonical and canonical["basis"] == "exact" else None
system = await systems_svc.create_system(
uid, project_id=project_id, name=data["name"],
description=data.get("description"), color=data.get("color"),
order_index=data.get("order_index", 0),
canonical_id=data.get("canonical_id") or applied,
)
if system is None:
return jsonify({"error": "Permission denied"}), 403
return jsonify(system.to_dict()), 201
out = system.to_dict()
if canonical and canonical["basis"] == "overlap" and not system.canonical_id:
out["canonical_suggestion"] = canonical
return jsonify(out), 201
@systems_bp.route("/<int:project_id>/systems/<int:system_id>", methods=["GET"])
+153 -7
View File
@@ -11,6 +11,8 @@ from scribe.models.note_supersession import NoteSupersession
from scribe.models.note_version import NoteVersion
from scribe.models.design_system import DesignSystem, DesignToken
from scribe.models.note_usage import NoteUsageEvent
from scribe.models.canonical_system import CanonicalSystem
from scribe.models.rulebook import RuleRelation, rule_systems as rule_systems_t
from scribe.models.code_shape import CodeShape, CodeShapeEvent, CodeShapeUse
from scribe.models.project import Project
from scribe.models.repo_binding import RepoBinding
@@ -69,11 +71,18 @@ _BACKED_UP = [
"note_usage_events", "repo_bindings", "note_supersessions",
# v7 (2026-08): the shape ledger (#2787); v8: its history (#2793).
"code_shapes", "code_shape_events", "code_shape_uses",
# v9 (2026-08): the global area catalog (milestone 307). Global, not
# user-scoped, so it rides in EVERY export — including a single-user
# one, whose Systems would otherwise restore unmapped.
"canonical_systems",
# v10 (2026-08): a rule's area tag and its typed edges (milestone 307).
"rule_systems", "rule_relations",
]
# Tables intentionally NOT in the backup, surfaced in the payload so the gap is
# explicit rather than silent. ACL (groups/shares) is a coherent follow-up;
# note_embeddings are derived (regenerated from note bodies); api_keys are
# note_embeddings and rule_embeddings are derived (regenerated at startup
# from the records themselves, which is also how a chunker bump is handled); api_keys are
# sensitive credentials; retrieval_logs is observational telemetry that nothing
# reads for correctness and that grows per query; the rest are
# transient/operational.
@@ -83,7 +92,7 @@ _BACKED_UP = [
# like coverage while naming nothing the schema could confirm.
_NOT_INCLUDED = [
"groups", "group_memberships", "project_shares", "note_shares",
"api_keys", "note_embeddings", "app_logs", "notifications",
"api_keys", "note_embeddings", "rule_embeddings", "app_logs", "notifications",
"invitation_tokens", "password_reset_tokens", "user_profiles",
"retrieval_logs",
# Sensitive credentials, same reasoning as api_keys: a backup that carries
@@ -127,12 +136,29 @@ def _rulebook_exclusion_rows(rows) -> list[dict]:
# same reason: CI has no database, so a serialiser that is a plain function is
# one that can actually be tested.
def _system_rows(rows) -> list[dict]:
def _canonical_system_rows(rows) -> list[dict]:
"""The global area catalog. Carried WITHOUT ids: a restore matches on slug,
so a target install that already seeded the standard vocabulary reuses its
own rows and only gains the entries an admin added here."""
return [
{
"name": r.name, "slug": r.slug, "description": r.description,
"order_index": r.order_index,
}
for r in rows
]
def _system_rows(rows, canonical_slugs: dict[int, str]) -> list[dict]:
"""A project's Systems. The canonical mapping travels as a SLUG, not an id
— the catalog is global and its ids are per-install, so an id would restore
pointing at whatever area happened to land on that number."""
return [
{
"id": r.id, "user_id": r.user_id, "project_id": r.project_id,
"name": r.name, "description": r.description, "color": r.color,
"status": r.status, "order_index": r.order_index,
"canonical_slug": canonical_slugs.get(r.canonical_id or 0),
}
for r in rows
]
@@ -332,12 +358,34 @@ def _topic_rows(rows) -> list[dict]:
]
def _rule_system_rows(rows) -> list[dict]:
"""A rule's area tags, carried by canonical SLUG for the same reason the
Systems are: the catalog is global and its ids are per-install."""
return [{"rule_id": rule_id, "canonical_slug": slug} for rule_id, slug in rows]
def _rule_relation_rows(rows) -> list[dict]:
"""The typed edges between rules. Carried because they are a JUDGEMENT —
someone decided these two fail together, or that one supersedes the other,
and nothing in either rule's text records the decision. Lose them and a
split rule silently starts arriving half at a time again."""
return [
{
"from_rule_id": r.from_rule_id, "to_rule_id": r.to_rule_id,
"kind": r.kind, "note": r.note,
}
for r in rows
]
def _rule_rows(rows) -> list[dict]:
return [
{
"id": r.id, "topic_id": r.topic_id, "project_id": r.project_id,
"title": r.title, "statement": r.statement, "why": r.why,
"how_to_apply": r.how_to_apply, "order_index": r.order_index,
"when_to_apply": r.when_to_apply, "tier": r.tier,
"arose_from_id": r.arose_from_id,
"created_at": r.created_at.isoformat(),
"updated_at": r.updated_at.isoformat(),
}
@@ -363,6 +411,15 @@ async def export_full_backup() -> dict:
)).scalars().all()
settings = (await session.execute(select(Setting))).scalars().all()
systems = (await session.execute(select(System))).scalars().all()
canonical_systems = (await session.execute(
select(CanonicalSystem).where(CanonicalSystem.deleted_at.is_(None))
.order_by(CanonicalSystem.order_index)
)).scalars().all()
rule_system_rows = (await session.execute(
select(rule_systems_t.c.rule_id, CanonicalSystem.slug)
.join(CanonicalSystem, CanonicalSystem.id == rule_systems_t.c.canonical_id)
)).all()
rule_relations = (await session.execute(select(RuleRelation))).scalars().all()
record_systems = (await session.execute(select(RecordSystem))).scalars().all()
supersessions = (
await session.execute(select(NoteSupersession))
@@ -424,7 +481,12 @@ async def export_full_backup() -> dict:
"rule_suppressions": _rule_suppression_rows(rule_suppressions),
"topic_suppressions": _topic_suppression_rows(topic_suppressions),
"rulebook_exclusions": _rulebook_exclusion_rows(rulebook_exclusions),
"systems": _system_rows(systems),
"canonical_systems": _canonical_system_rows(canonical_systems),
"rule_systems": _rule_system_rows(rule_system_rows),
"rule_relations": _rule_relation_rows(rule_relations),
"systems": _system_rows(
systems, {c.id: c.slug for c in canonical_systems}
),
"record_systems": _record_system_rows(record_systems),
"design_systems": _design_system_rows(design_systems),
"design_tokens": _design_token_rows(design_tokens),
@@ -467,6 +529,12 @@ async def export_user_backup(user_id: int) -> dict:
systems = (await session.execute(
select(System).where(System.user_id == user_id)
)).scalars().all()
# Global: taken whole even in a per-user export, because the Systems
# above reference it and a partial catalog restores partial mappings.
canonical_systems = (await session.execute(
select(CanonicalSystem).where(CanonicalSystem.deleted_at.is_(None))
.order_by(CanonicalSystem.order_index)
)).scalars().all()
system_ids = [sy.id for sy in systems]
note_ids = [n.id for n in notes]
# Scoped by the user's SYSTEMS, not their notes: a shared note carrying
@@ -533,6 +601,20 @@ async def export_user_backup(user_id: int) -> dict:
rules = (await session.execute(
select(Rule).where(or_(*rule_filters))
)).scalars().all() if rule_filters else []
# Scoped to the rules this export already carries: an edge whose far
# end is absent would restore pointing at nothing.
_rule_ids = [r.id for r in rules]
rule_system_rows = (await session.execute(
select(rule_systems_t.c.rule_id, CanonicalSystem.slug)
.join(CanonicalSystem, CanonicalSystem.id == rule_systems_t.c.canonical_id)
.where(rule_systems_t.c.rule_id.in_(_rule_ids))
)).all() if _rule_ids else []
rule_relations = (await session.execute(
select(RuleRelation).where(
RuleRelation.from_rule_id.in_(_rule_ids),
RuleRelation.to_rule_id.in_(_rule_ids),
)
)).scalars().all() if _rule_ids else []
if project_ids:
subscriptions = (await session.execute(
select(project_rulebook_subscriptions).where(
@@ -583,7 +665,12 @@ async def export_user_backup(user_id: int) -> dict:
"rule_suppressions": _rule_suppression_rows(rule_suppressions),
"topic_suppressions": _topic_suppression_rows(topic_suppressions),
"rulebook_exclusions": _rulebook_exclusion_rows(rulebook_exclusions),
"systems": _system_rows(systems),
"canonical_systems": _canonical_system_rows(canonical_systems),
"rule_systems": _rule_system_rows(rule_system_rows),
"rule_relations": _rule_relation_rows(rule_relations),
"systems": _system_rows(
systems, {c.id: c.slug for c in canonical_systems}
),
"record_systems": _record_system_rows(record_systems),
"design_systems": _design_system_rows(design_systems),
"design_tokens": _design_token_rows(design_tokens),
@@ -697,7 +784,8 @@ async def _restore_v2(data: dict) -> dict:
"systems": 0, "record_systems": 0, "design_systems": 0,
"design_tokens": 0, "note_usage_events": 0, "repo_bindings": 0,
"note_supersessions": 0, "code_shapes": 0, "code_shape_events": 0,
"code_shape_uses": 0,
"code_shape_uses": 0, "canonical_systems": 0,
"rule_systems": 0, "rule_relations": 0,
}
async with async_session() as session:
@@ -914,6 +1002,11 @@ async def _restore_v2(data: dict) -> dict:
statement=r_data.get("statement", ""),
why=r_data.get("why") or None,
how_to_apply=r_data.get("how_to_apply") or None,
when_to_apply=r_data.get("when_to_apply") or None,
# A file written before migration 0088 has no tier. always_on
# is the pre-0088 behaviour, so an old backup restores rules
# that bind exactly as they did when it was taken.
tier=r_data.get("tier") or "always_on",
order_index=r_data.get("order_index", 0),
created_at=_dt(r_data.get("created_at")),
updated_at=_dt(r_data.get("updated_at")),
@@ -970,8 +1063,58 @@ async def _restore_v2(data: dict) -> dict:
# --- v5 sections. Every one is data.get()-guarded, so a v2/v3/v4
# payload restores without them rather than failing on an absent key.
# 15. Systems
system_id_map: dict[int, int] = {}
# 14c. The global area catalog, matched on SLUG. This install already
# has the standard vocabulary from its migrations, so the common case
# adds nothing and simply learns which local id each slug is; only an
# entry an admin added on the source instance is created here. Runs
# BEFORE systems, which resolve their mapping through this map.
canonical_id_by_slug: dict[str, int] = {}
existing_canonical = (await session.execute(
select(CanonicalSystem).where(CanonicalSystem.deleted_at.is_(None))
)).scalars().all()
for entry in existing_canonical:
canonical_id_by_slug[entry.slug] = entry.id
for cs_data in data.get("canonical_systems", []):
slug = cs_data.get("slug") or ""
if not slug or slug in canonical_id_by_slug:
continue
entry = CanonicalSystem(
name=cs_data.get("name", ""), slug=slug,
description=cs_data.get("description"),
order_index=cs_data.get("order_index", 0),
)
session.add(entry)
await session.flush()
canonical_id_by_slug[slug] = entry.id
stats["canonical_systems"] += 1
# 14d. A rule's area tags and its typed edges. Runs HERE, not beside the
# rules in section 11, because it needs both maps: the rule ids from
# there and the canonical slugs from 14c just above.
for rs in data.get("rule_systems", []):
mapped_rule = rule_id_map.get(rs.get("rule_id", 0))
canonical_id = canonical_id_by_slug.get(rs.get("canonical_slug") or "")
if mapped_rule is None or canonical_id is None:
continue
await session.execute(rule_systems_t.insert().values(
rule_id=mapped_rule, canonical_id=canonical_id,
))
stats["rule_systems"] += 1
for rr in data.get("rule_relations", []):
mapped_from = rule_id_map.get(rr.get("from_rule_id", 0))
mapped_to = rule_id_map.get(rr.get("to_rule_id", 0))
if mapped_from is None or mapped_to is None or mapped_from == mapped_to:
continue
session.add(RuleRelation(
from_rule_id=mapped_from, to_rule_id=mapped_to,
kind=rr.get("kind", "co_surfaces"), note=rr.get("note") or None,
))
stats["rule_relations"] += 1
# 15. Systems
for sy_data in data.get("systems", []):
mapped_uid = user_id_map.get(sy_data.get("user_id", 0))
mapped_pid = project_id_map.get(sy_data.get("project_id", 0))
@@ -984,6 +1127,9 @@ async def _restore_v2(data: dict) -> dict:
color=sy_data.get("color"),
status=sy_data.get("status", "active"),
order_index=sy_data.get("order_index", 0),
# An unknown slug restores UNMAPPED rather than failing: the
# System and its records are the payload, the mapping is an aid.
canonical_id=canonical_id_by_slug.get(sy_data.get("canonical_slug") or ""),
)
session.add(system)
await session.flush()
+290
View File
@@ -0,0 +1,290 @@
"""The global canonical area vocabulary, and the mapping from a project's
Systems onto it (milestone 307 step 1, decision note 3026).
A `System` is per-project. Nothing outside a project can reference one, so a
rule that spans projects has no way to say "this is about CI" without chaining
itself to one project's row. `CanonicalSystem` is that join key, and it is
GLOBAL — no `user_id`, so a shared project inherits the vocabulary instead of
re-earning it.
Two rules govern everything here:
- **Associate, never rewrite.** Mapping a System sets `systems.canonical_id`
and nothing else. The local name stays whatever the project calls the area,
and `record_systems` is never touched — no record's tags move.
- **Propose, never decide.** An exact slug hit is mechanical and maps on
request; anything short of that is a PROPOSAL a human confirms. "CI &
Release" vs "CI & runners" is a judgment call, and the cost of guessing it
wrong silently is a rule surfacing in the wrong project.
Reads are open to any authenticated caller (the catalog is shared vocabulary,
not user data). Writes to the catalog itself are admin-only: a global table
that anyone can extend is how a shared vocabulary stops being shared.
"""
import logging
import re
from datetime import datetime, timezone
from sqlalchemy import select
from scribe.models import async_session
from scribe.models.canonical_system import CanonicalSystem
from scribe.models.system import System
from scribe.models.user import User
from scribe.services import access
logger = logging.getLogger(__name__)
# Tokens that carry no meaning for matching — "&" becomes "and" before the
# split, so it would otherwise dominate the overlap score of every pair.
_NOISE_TOKENS = frozenset({"and", "the", "a", "of"})
_NON_ALNUM = re.compile(r"[^a-z0-9]+")
def canonical_slug(name: str) -> str:
"""The match key for an area name — NOT a display value.
Folds exactly the spelling differences that produced three names for one
area on the author's instance: `CI & Release`, `CI and Release` and
`CI & release` all slug to `ci-and-release`, so they map mechanically.
A real difference survives: `CI & runners` slugs to `ci-and-runners` and
goes through the proposal path where a human decides.
"""
lowered = name.strip().lower().replace("&", " and ")
return "-".join(_NON_ALNUM.sub(" ", lowered).split())
def _tokens(slug: str) -> frozenset[str]:
return frozenset(slug.split("-")) - _NOISE_TOKENS
async def _is_admin(user_id: int) -> bool:
async with async_session() as session:
role = await session.scalar(select(User.role).where(User.id == user_id))
return role == "admin"
async def list_canonical_systems() -> list[CanonicalSystem]:
"""The whole catalog, in display order. Global — no ownership filter."""
async with async_session() as session:
result = await session.execute(
select(CanonicalSystem)
.where(CanonicalSystem.deleted_at.is_(None))
.order_by(CanonicalSystem.order_index.asc(), CanonicalSystem.name.asc())
)
return list(result.scalars().all())
async def get_canonical_system(canonical_id: int) -> CanonicalSystem | None:
async with async_session() as session:
entry = await session.get(CanonicalSystem, canonical_id)
return entry if entry is not None and entry.deleted_at is None else None
async def find_by_name(name: str) -> CanonicalSystem | None:
"""The exact-slug lookup — the mechanical half of matching."""
slug = canonical_slug(name)
if not slug:
return None
async with async_session() as session:
return await session.scalar(
select(CanonicalSystem).where(
CanonicalSystem.slug == slug,
CanonicalSystem.deleted_at.is_(None),
)
)
def _overlap(local: frozenset[str], other: frozenset[str]) -> float:
return len(local & other) / max(len(local | other), 1)
async def best_overlap(name: str, catalog: list | None = None) -> dict | None:
"""The closest catalog entry that shares a meaningful word, or None.
The ONE scorer behind both offers: the create-time suggestion and the
review surface. Two scorers would eventually disagree about which area a
name resembles, and the operator would be asked one question at create
time and a different one at review.
The threshold is any shared meaningful word, deliberately generous: a
wrong offer costs one dismissal, a missing one costs a mapping nobody
thinks to make again. Nothing here ever applies — `overlap` is always an
offer (see propose_mappings).
"""
slug = canonical_slug(name)
if not slug:
return None
local = _tokens(slug)
if not local:
return None
# A caller already holding the catalog passes it: this runs once per
# unmapped System in the review sweep, and re-reading the table each time
# would make an N+1 out of a report.
if catalog is None:
catalog = await list_canonical_systems()
best, best_score = None, 0.0
for entry in catalog:
score = _overlap(local, _tokens(entry.slug))
if score > best_score:
best, best_score = entry, score
if best is None or best_score <= 0:
return None
return {
"id": best.id, "name": best.name,
"basis": "overlap", "score": round(best_score, 3),
}
async def create_canonical_system(
user_id: int, name: str, description: str | None = None,
) -> CanonicalSystem | dict | None:
"""Add an area to the global catalog. Admin only.
Duplicate-gated on the SLUG, not the raw name, so "CI and Release" cannot
be added alongside "CI & Release" — that is the drift this table exists to
end. Returns the existing entry's id instead of creating a second one.
"""
if not await _is_admin(user_id):
return None
slug = canonical_slug(name)
if not slug:
return None
existing = await find_by_name(name)
if existing is not None:
return {
"duplicate": True,
"existing_id": existing.id,
"message": (
f"'{existing.name}' (#{existing.id}) already covers this area — "
f"both names reduce to '{slug}'. Map Systems to it, or "
"update_canonical_system if the charter needs revising."
),
}
async with async_session() as session:
highest = await session.scalar(
select(CanonicalSystem.order_index)
.order_by(CanonicalSystem.order_index.desc())
.limit(1)
)
entry = CanonicalSystem(
name=" ".join(name.split()),
slug=slug,
description=description,
order_index=(highest or 0) + 1,
)
session.add(entry)
await session.commit()
await session.refresh(entry)
return entry
async def update_canonical_system(
user_id: int, canonical_id: int, **fields: object,
) -> CanonicalSystem | None:
"""Rename or re-charter a catalog entry. Admin only.
A rename recomputes the slug — the display name and the match key must not
be allowed to disagree, or the exact-match path silently stops finding it.
"""
if not await _is_admin(user_id):
return None
allowed = {"name", "description", "order_index"}
async with async_session() as session:
entry = await session.get(CanonicalSystem, canonical_id)
if entry is None or entry.deleted_at is not None:
return None
for key, value in fields.items():
if key in allowed and value is not None:
setattr(entry, key, value)
if "name" in fields and fields["name"]:
entry.name = " ".join(str(fields["name"]).split())
entry.slug = canonical_slug(entry.name)
entry.updated_at = datetime.now(timezone.utc)
await session.commit()
await session.refresh(entry)
return entry
async def set_system_canonical(
user_id: int, system_id: int, canonical_id: int | None,
) -> System | None:
"""Map (or unmap) one project System onto a catalog entry.
Authorised by the PROJECT, not the catalog: mapping changes the project's
row, so project write access is the right gate (rule 78 — never a bare
owner filter). Passing None clears the mapping.
Touches `canonical_id` and nothing else — the System's own name, charter
and record associations are left exactly as they are.
"""
if canonical_id is not None and await get_canonical_system(canonical_id) is None:
return None
async with async_session() as session:
system = await session.get(System, system_id)
if system is None or system.deleted_at is not None:
return None
if not await access.can_write_project(user_id, system.project_id):
return None
system.canonical_id = canonical_id
system.updated_at = datetime.now(timezone.utc)
await session.commit()
await session.refresh(system)
return system
async def propose_mappings(user_id: int, project_id: int) -> list[dict]:
"""Suggest a catalog entry for each of a project's UNMAPPED Systems.
Returns proposals, never applied changes — `set_system_canonical` is the
only thing that writes. Each carries a `basis` so the reviewer knows what
they are approving:
- `exact` — the two names reduce to the same slug. Mechanical.
- `overlap` — they share a meaningful word ("CI & runners" / "CI &
Release"). A judgment call, and the reason this is a proposal at all.
A System with no plausible match simply gets no proposal: unmapped is a
perfectly good resting state, so silence here is an answer, not a gap.
"""
if not await access.can_read_project(user_id, project_id):
return []
catalog = await list_canonical_systems()
if not catalog:
return []
async with async_session() as session:
result = await session.execute(
select(System).where(
System.project_id == project_id,
System.canonical_id.is_(None),
System.deleted_at.is_(None),
).order_by(System.order_index.asc(), System.created_at.asc())
)
systems = list(result.scalars().all())
by_slug = {entry.slug: entry for entry in catalog}
proposals: list[dict] = []
for system in systems:
slug = canonical_slug(system.name)
if not slug:
continue
exact = by_slug.get(slug)
if exact is not None:
match = {"id": exact.id, "name": exact.name, "basis": "exact", "score": 1.0}
else:
# Same scorer the create-time offer uses, so the two surfaces can
# never name different areas for one System.
match = await best_overlap(system.name, catalog)
if match is None:
continue
proposals.append({
"system_id": system.id,
"system_name": system.name,
"canonical_id": match["id"],
"canonical_name": match["name"],
"basis": match["basis"],
"score": match["score"],
})
proposals.sort(key=lambda p: (-p["score"], p["system_name"]))
return proposals
+196 -1
View File
@@ -16,13 +16,18 @@ import os
from collections.abc import Sequence
from typing import TYPE_CHECKING
from sqlalchemy import delete, or_, select
from scribe.models import async_session
from scribe.models.embedding import NoteEmbedding
from scribe.models.embedding import NoteEmbedding, RuleEmbedding
from scribe.models.note import Note
from scribe.services.access import notes_visibility_clause
if TYPE_CHECKING: # resolves the Rule forward ref without importing at runtime
from scribe.models.rulebook import Rule
logger = logging.getLogger(__name__)
# Minimum cosine similarity to include a note in context results.
@@ -612,3 +617,193 @@ async def backfill_note_embeddings() -> None:
await asyncio.sleep(0.05) # gentle pacing
logger.info("Embedding backfill complete: %d/%d notes embedded", success, len(notes_to_embed))
# ── Rules (milestone 307, note 3026) ────────────────────────────────────
def rule_document(
title: str | None, statement: str | None, when_to_apply: str | None,
) -> tuple[str | None, str | None]:
"""The (title, body) a rule is EMBEDDED as — trigger first, `why` never.
Both halves of this are measured, not guessed (note 2485). That pass found
the snippet was the only sharp record in the corpus — a 0.153 top-to-second
gap against 0.0100.023 for everything else — and that the cause was its
SHAPE: `{name}{when_to_use}` as the title and `**When to use:** …`
repeated in the body, so purpose appears twice in a short document and
dominates the vector. This mirrors that exactly.
And it excludes `why` on the same evidence. `why` is dated incident
narrative — rule 46's runs to 4,300 characters of it — and long,
multi-topic prose is precisely what made sixteen dev-logs mutually
indistinguishable: the average lands on the centroid of "development",
which every one of them shares. Adding `why` would not give the vector more
to work with; it would give every rule the same thing to work with.
A rule with no trigger yet degrades to title + statement. It still embeds,
just less sharply — which is an argument for backfilling triggers, not an
argument for padding the document with whatever text is lying around.
"""
trigger = (when_to_apply or "").strip()
name = (title or "").strip()
body = (statement or "").strip()
if not trigger:
return name or None, body or None
return (
f"{name}{trigger}" if name else trigger,
f"When to apply: {trigger}\n\n{body}" if body else f"When to apply: {trigger}",
)
async def upsert_rule_embedding(
rule_id: int, title: str | None, statement: str | None,
when_to_apply: str | None = None,
) -> None:
"""Chunk, embed and persist a rule's vectors. Safe to fire-and-forget.
The note twin's contract, for the same reasons: the document is built HERE
so the write path, the backfill and any re-embed share one definition, and
replacement is atomic per rule so a concurrent read sees the old chunk set
or the new one, never a mixture.
"""
doc_title, doc_body = rule_document(title, statement, when_to_apply)
chunks = chunk_document(doc_title, doc_body)
try:
if not chunks:
async with async_session() as session:
await session.execute(
delete(RuleEmbedding).where(RuleEmbedding.rule_id == rule_id)
)
await session.commit()
return
except Exception:
logger.warning("Failed to clear embedding for rule %d", rule_id, exc_info=True)
return
try:
vectors = await get_embeddings(chunks)
except Exception:
logger.debug("Skipping embedding for rule %d — embedder unavailable", rule_id)
return
try:
async with async_session() as session:
await session.execute(
delete(RuleEmbedding).where(RuleEmbedding.rule_id == rule_id)
)
for index, (chunk, vector) in enumerate(zip(chunks, vectors)):
session.add(
RuleEmbedding(
rule_id=rule_id,
chunk_index=index,
embedding=vector,
chunk_text=chunk,
chunker_version=CHUNKER_VERSION,
)
)
await session.commit()
except Exception:
logger.warning("Failed to persist embedding for rule %d", rule_id, exc_info=True)
async def semantic_search_rules(
user_id: int,
query: str,
limit: int = 5,
threshold: float = _SIMILARITY_THRESHOLD,
tier: str | None = None,
) -> list[tuple[float, "Rule"]]:
"""Return up to *limit* (score, rule) pairs most relevant to *query*.
Scoped by OWNERSHIP — a rule is the caller's if they own its rulebook or
its project. Deliberately not filtered to what currently BINDS a given
project: this answers "is there a rule about this", which a person asking
wants answered across their whole rulebook. Deciding which rules bind where
is the surfacing question, and it has its own machinery
(get_applicable_rules) rather than a second, subtly different copy here.
`tier` narrows to one tier. The write-path hint passes "conditional",
because an always-on rule is ALREADY in the session — surfacing it again as
a suggestion is pure noise, and noise on a hint that fires on every write
is how a hint gets ignored.
Collapses to best-chunk-per-rule like the note search, so a long rule split
across chunks competes once rather than crowding the results with itself.
Returns an empty list if the embedder is unavailable or on any error.
"""
from scribe.models.project import Project
from scribe.models.rulebook import Rule, Rulebook, RulebookTopic
if not query or not query.strip():
return []
try:
query_vec = await get_embedding(query)
except Exception:
logger.debug("Rule search skipped — embedder unavailable")
return []
max_distance = min(2.0, max(0.0, 1.0 - threshold))
distance = RuleEmbedding.embedding.cosine_distance(query_vec)
try:
async with async_session() as session:
rows = (await session.execute(
select(Rule, distance.label("distance"))
.select_from(RuleEmbedding)
.join(Rule, RuleEmbedding.rule_id == Rule.id)
.outerjoin(RulebookTopic, Rule.topic_id == RulebookTopic.id)
.outerjoin(Rulebook, RulebookTopic.rulebook_id == Rulebook.id)
.outerjoin(Project, Rule.project_id == Project.id)
.where(
Rule.deleted_at.is_(None),
distance <= max_distance,
# topic_id XOR project_id, so exactly one arm can match.
or_(
Rulebook.owner_user_id == user_id,
Project.user_id == user_id,
),
*( [Rule.tier == tier] if tier else [] ),
)
# Overfetch so collapsing chunks to their best row still fills
# the page — the same reason the note search overfetches.
.order_by(distance)
.limit(limit * _CHUNK_OVERFETCH)
)).all()
except Exception:
logger.warning("Rule semantic search failed", exc_info=True)
return []
best: dict[int, tuple[float, object]] = {}
for rule, dist in rows:
score = 1.0 - float(dist)
if rule.id not in best or score > best[rule.id][0]:
best[rule.id] = (score, rule)
ranked = sorted(best.values(), key=lambda pair: pair[0], reverse=True)
return ranked[:limit]
async def backfill_rule_embeddings() -> None:
"""Embed rules that have no current vectors. Runs at startup beside the
note backfill; a CHUNKER_VERSION bump re-embeds rather than wiping."""
from scribe.models.rulebook import Rule
try:
async with async_session() as session:
current = select(RuleEmbedding.rule_id).where(
RuleEmbedding.chunker_version == CHUNKER_VERSION
)
stale = (await session.execute(
select(Rule.id, Rule.title, Rule.statement, Rule.when_to_apply)
.where(Rule.deleted_at.is_(None), Rule.id.notin_(current))
)).all()
except Exception:
logger.warning("Rule embedding backfill: failed to query rules", exc_info=True)
return
if not stale:
logger.info("Rule embedding backfill: all rules current at chunker v%d", CHUNKER_VERSION)
return
logger.info("Rule embedding backfill: embedding %d rule(s)", len(stale))
for rule_id, title, statement, when_to_apply in stale:
await upsert_rule_embedding(rule_id, title, statement, when_to_apply)
+49 -2
View File
@@ -30,7 +30,7 @@ from scribe.services import rulebooks as rulebooks_svc
from scribe.services import shape_ledger as shape_ledger_svc
from scribe.services import snippets as snippets_svc
from scribe.services.access import label_shared_items, owner_names_for
from scribe.services.embeddings import semantic_search_notes
from scribe.services.embeddings import semantic_search_notes, semantic_search_rules
from scribe.services.note_usage import record_surfaced
from scribe.services.supersession import superseded_ids
from scribe.services.retrieval_telemetry import record_retrieval
@@ -707,6 +707,7 @@ async def build_write_path_hint(
stamp_shapes: list[tuple[str, str]] | None = None,
repo_key: str = "",
exclude_derive: list[str] | None = None,
exclude_rule_ids: list[int] | None = None,
) -> dict:
"""Prior-art hint for the plugin's PreToolUse hook on Write/Edit.
@@ -766,7 +767,8 @@ async def build_write_path_hint(
"""
cfg = await get_writepath_config(user_id)
empty = {"context": "", "note_ids": [], "sync_note_ids": [], "config": cfg,
"stamped": [], "divergence": [], "derive": [], "derive_keys": []}
"stamped": [], "divergence": [], "derive": [], "derive_keys": [],
"rule_ids": []}
path = (path or "").strip()
if not cfg["enabled"] or not path:
return empty
@@ -1036,6 +1038,50 @@ async def build_write_path_hint(
for arm, ids in by_arm.items():
record_surfaced(user_id=user_id, note_ids=ids, source=arm)
# ── Standing rules that may apply here (milestone 307) ──────────────
#
# A SUGGESTION, not a binding surface, and the distinction is the design
# (D7): a rule BINDS by being tagged to an area the project works in,
# resolved deterministically at enter_project. This arm reaches for
# something weaker and still useful — a conditional rule whose trigger
# resembles what is being written, noticed at the moment it is relevant
# rather than by being resident in every session.
#
# CONDITIONAL ONLY. An always-on rule is already in the session; repeating
# it here would be noise, and noise on a hint that fires on every write is
# how a hint gets ignored.
#
# Fails open like every other arm: a rule hint must never break a write.
rule_ids: list[int] = []
try:
already = set(exclude_rule_ids or [])
hits = await semantic_search_rules(
user_id, code or path, limit=2,
threshold=cfg["threshold"], tier="conditional",
)
fresh = [(score, rule) for score, rule in hits if rule.id not in already]
for _score, rule in fresh:
trigger = (rule.when_to_apply or "").strip()
lines.append(
f"Standing rule that may apply here — \u201c{rule.title}\u201d"
+ (f" ({trigger})" if trigger else "")
+ f". Read it with get_rule({rule.id}) before deciding it "
"does not apply; it is not in this session's loaded set."
)
rule_ids.append(rule.id)
if fresh:
# retrieval_logs, NOT note_usage_events: that table's ids are
# remapped on a backup restore, so a rule id there would return
# attached to whatever note took that number. This one is never
# restored, and `source` already separates the surfaces.
record_retrieval(
user_id=user_id, source="write_path_rule", query=code or path,
threshold=cfg["threshold"], limit=2, project_id=project_id,
is_task=None, results=fresh,
)
except Exception:
logger.debug("write-path rule arm failed", exc_info=True)
return {
"context": "\n".join(lines),
"note_ids": note_ids,
@@ -1045,6 +1091,7 @@ async def build_write_path_hint(
"divergence": divergence,
"derive": derive,
"derive_keys": [d["key"] for d in derive],
"rule_ids": rule_ids,
}
+10 -1
View File
@@ -17,6 +17,7 @@ from __future__ import annotations
import asyncio
import logging
from typing import Any
from datetime import datetime, timedelta, timezone
@@ -108,11 +109,19 @@ def record_retrieval(
limit: int | None,
project_id: int | None,
is_task: bool | None,
results: list[tuple[float, Note]],
results: list[tuple[float, Any]],
duration_ms: float | None = None,
) -> None:
"""Fire-and-forget: record one retrieval call.
`results` needs only `.id` on each record, which is why it is not typed to
Note: rules are retrieved too (milestone 307) and land here rather than in
note_usage_events. That table's ids are REMAPPED on a backup restore, so a
rule id written into it would come back attached to whatever note happened
to take that number — silent corruption of the very evidence this exists to
provide. retrieval_logs is not restored at all, so it has no such hazard,
and `source` already distinguishes the surfaces.
Builds the payload inline (synchronously) then schedules the insert so the
caller returns immediately. Never raises — telemetry must not affect search.
"""
+401 -18
View File
@@ -10,9 +10,10 @@ from __future__ import annotations
import logging
from typing import Optional
from sqlalchemy import select
from sqlalchemy import delete as sql_delete, insert, or_, select
from scribe.models import async_session
from scribe.models.system import System
from scribe.models.rulebook import Rulebook
logger = logging.getLogger(__name__)
@@ -223,7 +224,7 @@ async def delete_topic(topic_id: int, user_id: int) -> None:
# ── Rule CRUD ──────────────────────────────────────────────────────────
from scribe.models.rulebook import Rule
from scribe.models.rulebook import Rule, RuleRelation, rule_systems
async def _assert_topic_owned(session, topic_id: int, user_id: int) -> None:
@@ -280,9 +281,161 @@ async def _assert_rulebook_rule_owned(session, rule_id: int, user_id: int) -> No
raise ValueError(f"rule {rule_id} not found or not a rulebook rule")
# The vocabularies migration 0088's CHECK constraints enforce. Named here so
# a caller can be corrected before the database refuses it (rule 36 keeps the
# two in step; this keeps the error readable).
TIERS = ("always_on", "conditional")
RELATION_KINDS = ("co_surfaces", "overrides", "elaborates")
def _valid_tier(tier: str) -> str:
"""An unrecognised tier falls back to always_on — the SAFE direction.
Getting this wrong the other way would silently stop a rule binding, which
is the one failure this whole milestone exists to prevent. A rule that
preloads when it did not need to costs context; a rule that quietly stops
preloading costs the behaviour it was written for.
"""
return tier if tier in TIERS else "always_on"
def rule_brief(rule: Rule, **extra) -> dict:
"""The shape a rule takes when it is SURFACED rather than opened.
One builder for every payload that hands rules to an agent, because there
were three copies of this dict and they had already diverged — two carried
`topic_id`, one didn't, and none carried the timestamps the model has held
all along. That omission is why a rule written before the capability it
duplicates was indistinguishable, at read time, from one still doing work
(the FabledCurator case, note 3026).
`updated_at` is a DATE, not a stamp: the question it answers is "how old
is this?", and a full ISO string across an always-on set is ~2k characters
of payload for a precision nobody reads.
`why` and `how_to_apply` are deliberately NOT here — they are the depth a
caller gets from get_rule, and putting them in every listing is the bloat
this milestone is about.
"""
out = {
"id": rule.id,
"title": rule.title,
"statement": rule.statement,
"topic_id": rule.topic_id,
"tier": rule.tier,
"updated_at": rule.updated_at.date().isoformat() if rule.updated_at else None,
}
# Attached only when present (#2483: never a null key that reads as a
# capability the record doesn't have).
if rule.when_to_apply:
out["when_to_apply"] = rule.when_to_apply
if rule.arose_from_id:
out["arose_from_id"] = rule.arose_from_id
out.update({k: v for k, v in extra.items() if v is not None})
return out
def _refresh_rule_embedding(rule: Rule) -> None:
"""Re-index a rule after a write. Fire-and-forget, like the note twin.
Lazy import so this module doesn't pull in the embedder; every exception
swallowed because a rule that SAVED must not fail on its index refresh —
a stale vector costs a missed search hit, a raised exception costs the
write. No running loop (unit tests, scripts) is ordinary, not an error.
"""
try:
import asyncio
from scribe.services.embeddings import upsert_rule_embedding
asyncio.create_task(
upsert_rule_embedding(
rule.id, rule.title, rule.statement, rule.when_to_apply,
)
)
except RuntimeError:
pass # no running loop — a sync caller, not a failure
except Exception: # noqa: BLE001 - never let indexing break a write
logger.exception("embedding refresh failed for rule %s", rule.id)
async def co_surfaced_partners(
user_id: int, rule_ids: list[int], exclude_ids: set[int] | None = None,
) -> list[Rule]:
"""Rules that must arrive WITH the given ones, because they fail together.
This is the whole reason `co_surfaces` exists. Rule 144 was split off rule
46 and folded back into it the same day, on the correct observation that
"either rule could surface without the other and miss exposing a project to
what the entire shape is intended to be." Merging was the only fix
available; this is the fix that should have been available.
Two limits, both deliberate:
- Only rules the caller OWNS. An edge is not a back door into someone
else's rulebook.
- `exclude_ids` is honoured, and callers pass the project's SUPPRESSIONS.
A project that explicitly muted a rule should not have it dragged back in
by an edge — the suppression is a decision, and the edge does not
outrank it.
"""
if not rule_ids:
return []
known = set(rule_ids) | (exclude_ids or set())
async with async_session() as session:
edges = (await session.execute(
select(RuleRelation).where(
RuleRelation.kind == "co_surfaces",
or_(
RuleRelation.from_rule_id.in_(rule_ids),
RuleRelation.to_rule_id.in_(rule_ids),
),
)
)).scalars().all()
partners = {
(edge.to_rule_id if edge.from_rule_id in known else edge.from_rule_id)
for edge in edges
} - known
if not partners:
return []
# Ownership re-checked per partner rather than assumed from the edge.
out = []
for partner_id in sorted(partners):
rule = await _fetch_owned_rule(session, partner_id, user_id)
if rule is not None:
out.append(rule)
return out
async def rule_detail(user_id: int, rule: Rule, system_ids: list[int] | None = None) -> dict:
"""The full record, with its areas and edges attached.
ONE seam for both doors and every write path, so create, update and get
cannot disagree about what a rule looks like coming back — the same
reasoning as attach_relations for notes (#2859), and the same reasoning
rule_brief exists for one level down.
`system_ids=None` means "leave the tags alone"; a list (including [])
REPLACES them.
"""
if system_ids is not None:
await set_rule_systems(rule.id, user_id, system_ids)
data = rule.to_dict()
systems = (await list_rule_systems([rule.id])).get(rule.id, [])
relations = (await list_rule_relations([rule.id])).get(rule.id, [])
# Attached only when present (#2483): an empty key reads as a capability
# the record has and isn't using, which is a different claim.
if systems:
data["systems"] = systems
if relations:
data["relations"] = relations
return data
async def create_rule(
topic_id: int, user_id: int, title: str, statement: str,
why: str = "", how_to_apply: str = "", order_index: int = 0,
when_to_apply: str = "", tier: str = "always_on", arose_from_id: int = 0,
) -> Rule:
async with async_session() as session:
await _assert_topic_owned(session, topic_id, user_id)
@@ -290,19 +443,24 @@ async def create_rule(
topic_id=topic_id,
title=title,
statement=statement,
when_to_apply=when_to_apply or None,
tier=_valid_tier(tier),
why=why or None,
how_to_apply=how_to_apply or None,
arose_from_id=arose_from_id or None,
order_index=order_index,
)
session.add(rule)
await session.commit()
await session.refresh(rule)
_refresh_rule_embedding(rule)
return rule
async def create_project_rule(
project_id: int, user_id: int, title: str, statement: str,
why: str = "", how_to_apply: str = "", order_index: int = 0,
when_to_apply: str = "", tier: str = "always_on", arose_from_id: int = 0,
) -> Rule:
"""Create a rule scoped to a single project (no rulebook ceremony).
@@ -316,13 +474,17 @@ async def create_project_rule(
project_id=project_id,
title=title,
statement=statement,
when_to_apply=when_to_apply or None,
tier=_valid_tier(tier),
why=why or None,
how_to_apply=how_to_apply or None,
arose_from_id=arose_from_id or None,
order_index=order_index,
)
session.add(rule)
await session.commit()
await session.refresh(rule)
_refresh_rule_embedding(rule)
return rule
@@ -454,6 +616,17 @@ async def list_always_on_rules(
Rule.deleted_at.is_(None),
RulebookTopic.deleted_at.is_(None),
Rulebook.deleted_at.is_(None),
# TIER (milestone 307). This is the SESSION-START call, made
# before any project is in scope — there is no area vocabulary
# to match a conditional rule against yet, so only the
# unconditional tier belongs here. A conditional rule reaches a
# session through enter_project (by area) or search (by
# meaning), not by being resident.
#
# Behaviour is unchanged until rules are actually re-tiered:
# `tier` defaults to always_on, so every existing rule still
# arrives exactly as it did.
Rule.tier == "always_on",
)
)
if project_id:
@@ -513,15 +686,175 @@ async def update_rule(rule_id: int, user_id: int, **fields) -> Optional[Rule]:
rule = await _fetch_owned_rule(session, rule_id, user_id)
if rule is None:
return None
allowed = {"title", "statement", "why", "how_to_apply", "order_index"}
allowed = {
"title", "statement", "why", "how_to_apply", "order_index",
"when_to_apply", "tier", "arose_from_id",
}
for key, value in fields.items():
if key in allowed and value is not None:
setattr(rule, key, value)
setattr(rule, key, _valid_tier(value) if key == "tier" else value)
await session.commit()
await session.refresh(rule)
_refresh_rule_embedding(rule)
return rule
# ── Canon tags + typed edges (milestone 307) ───────────────────────────
async def set_rule_systems(
rule_id: int, user_id: int, canonical_ids: list[int],
) -> list[int] | None:
"""Replace which global AREAS a rule is about. None if not owned.
Set-semantics like set_record_systems: the list given IS the state after,
so an empty list clears the tags. Points at the canonical catalog, never a
project's System — a family rule tagged to one project's row would bind
itself to that project's vocabulary.
"""
from scribe.models.canonical_system import CanonicalSystem
from scribe.models.rulebook import rule_systems as rule_systems_t
async with async_session() as session:
rule = await _fetch_owned_rule(session, rule_id, user_id)
if rule is None:
return None
wanted = set(canonical_ids or [])
if wanted:
live = set((await session.execute(
select(CanonicalSystem.id).where(
CanonicalSystem.id.in_(wanted),
CanonicalSystem.deleted_at.is_(None),
)
)).scalars().all())
# Silently dropping an unknown id would leave the caller believing
# a tag exists; keep only the live ones and report what stuck.
wanted &= live
await session.execute(
sql_delete(rule_systems_t).where(rule_systems_t.c.rule_id == rule_id)
)
for canonical_id in sorted(wanted):
await session.execute(
insert(rule_systems_t).values(rule_id=rule_id, canonical_id=canonical_id)
)
await session.commit()
return sorted(wanted)
async def list_rule_systems(rule_ids: list[int]) -> dict[int, list[dict]]:
"""The canon tags for a batch of rules, keyed by rule id.
Batched on purpose: the surfacing paths ask about a whole payload of rules
at once, and one query per rule would turn every session start into an
N+1.
"""
from scribe.models.canonical_system import CanonicalSystem
from scribe.models.rulebook import rule_systems as rule_systems_t
if not rule_ids:
return {}
async with async_session() as session:
rows = (await session.execute(
select(rule_systems_t.c.rule_id, CanonicalSystem.id, CanonicalSystem.name)
.join(CanonicalSystem, CanonicalSystem.id == rule_systems_t.c.canonical_id)
.where(
rule_systems_t.c.rule_id.in_(rule_ids),
CanonicalSystem.deleted_at.is_(None),
)
.order_by(CanonicalSystem.order_index)
)).all()
out: dict[int, list[dict]] = {}
for rule_id, canonical_id, name in rows:
out.setdefault(rule_id, []).append({"id": canonical_id, "name": name})
return out
async def add_rule_relation(
user_id: int, from_rule_id: int, to_rule_id: int, kind: str, note: str = "",
) -> RuleRelation | None:
"""Draw a typed edge between two rules. None if either isn't owned.
Both ends are ownership-checked: an edge is only meaningful if the drawer
can see both rules, and a one-sided edge would surface a rule the caller
has no business reading.
Idempotent — re-drawing an existing edge returns it rather than raising, so
a true-up pass can be re-run without cleaning up first.
"""
if kind not in RELATION_KINDS:
raise ValueError(f"kind must be one of {RELATION_KINDS}, got {kind!r}")
if from_rule_id == to_rule_id:
raise ValueError("a rule cannot relate to itself")
async with async_session() as session:
for rid in (from_rule_id, to_rule_id):
if await _fetch_owned_rule(session, rid, user_id) is None:
return None
existing = await session.scalar(
select(RuleRelation).where(
RuleRelation.from_rule_id == from_rule_id,
RuleRelation.to_rule_id == to_rule_id,
RuleRelation.kind == kind,
)
)
if existing is not None:
return existing
relation = RuleRelation(
from_rule_id=from_rule_id, to_rule_id=to_rule_id,
kind=kind, note=note or None,
)
session.add(relation)
await session.commit()
await session.refresh(relation)
return relation
async def remove_rule_relation(user_id: int, relation_id: int) -> bool:
async with async_session() as session:
relation = await session.get(RuleRelation, relation_id)
if relation is None:
return False
if await _fetch_owned_rule(session, relation.from_rule_id, user_id) is None:
return False
await session.delete(relation)
await session.commit()
return True
async def list_rule_relations(rule_ids: list[int]) -> dict[int, list[dict]]:
"""Edges touching a batch of rules, keyed by rule id.
`co_surfaces` is reported from BOTH ends off a single stored row — it means
"these fail together", which is not a claim with a direction. The other two
are directional and are reported as stored, with `direction` naming which
end this rule is: an override read from the wrong end would invert what it
says.
"""
if not rule_ids:
return {}
async with async_session() as session:
rows = (await session.execute(
select(RuleRelation).where(
(RuleRelation.from_rule_id.in_(rule_ids))
| (RuleRelation.to_rule_id.in_(rule_ids))
)
)).scalars().all()
out: dict[int, list[dict]] = {}
wanted = set(rule_ids)
for relation in rows:
if relation.from_rule_id in wanted:
out.setdefault(relation.from_rule_id, []).append({
"id": relation.id, "kind": relation.kind,
"rule_id": relation.to_rule_id,
"direction": "outgoing", "note": relation.note or "",
})
if relation.to_rule_id in wanted:
out.setdefault(relation.to_rule_id, []).append({
"id": relation.id, "kind": relation.kind,
"rule_id": relation.from_rule_id,
"direction": "incoming", "note": relation.note or "",
})
return out
async def delete_rule(rule_id: int, user_id: int) -> None:
async with async_session() as session:
rule = await _fetch_owned_rule(session, rule_id, user_id)
@@ -533,7 +866,6 @@ async def delete_rule(rule_id: int, user_id: int) -> None:
# ── Subscriptions + get_applicable_rules ───────────────────────────────
from sqlalchemy import insert, delete as sql_delete
from sqlalchemy.exc import IntegrityError
@@ -802,10 +1134,13 @@ async def get_applicable_rules(
# Applicable rules (limit + 1 so we can detect truncation). Filter
# in SQL so truncation reflects the post-suppression count, not the
# raw subscription count.
# Selects the ENTITY, not a column list: rule_brief is the one place
# that decides which fields a surfaced rule carries, and a column list
# here would be a second such decision to keep in step. The row count
# is bounded by `limit`, so this is a listing, not a scan.
rules_q = (
select(
Rule.id, Rule.title, Rule.statement,
RulebookTopic.id.label("topic_id"),
Rule,
RulebookTopic.title.label("topic_title"),
Rulebook.id.label("rulebook_id"),
Rulebook.title.label("rulebook_title"),
@@ -835,21 +1170,41 @@ async def get_applicable_rules(
rules_q = rules_q.where(Rule.id.notin_(suppressed_rule_ids))
if suppressed_topic_ids:
rules_q = rules_q.where(Rule.topic_id.notin_(suppressed_topic_ids))
# TIER (milestone 307). always_on rules are resident, as every rule was
# before tiers existed. A conditional rule is REACHABLE, and reaches
# this project only when it is tagged to an area this project actually
# works in — a deterministic tag match, never a similarity score, so
# bindingness never depends on a ranking (D7).
#
# Applied in SQL rather than by filtering afterwards, so `limit` counts
# the rules that will actually be surfaced instead of counting rules
# that are about to be dropped.
project_area_ids = (await session.execute(
select(System.canonical_id).where(
System.project_id == project_id,
System.canonical_id.is_not(None),
System.deleted_at.is_(None),
System.status == "active",
).distinct()
)).scalars().all()
reachable = select(rule_systems.c.rule_id).where(
rule_systems.c.canonical_id.in_(project_area_ids)
) if project_area_ids else None
tier_clause = (Rule.tier == "always_on")
if reachable is not None:
tier_clause = or_(tier_clause, Rule.id.in_(reachable))
rules_q = rules_q.where(tier_clause)
rule_rows = (await session.execute(rules_q)).all()
truncated = len(rule_rows) > limit
rules = [
{
"id": rid, "title": rtitle, "statement": stmt,
"topic_id": ti, "topic_title": tt,
"rulebook_id": rbi, "rulebook_title": rbt,
}
for rid, rtitle, stmt, ti, tt, rbi, rbt in rule_rows[:limit]
rule_brief(rule, topic_title=tt, rulebook_id=rbi, rulebook_title=rbt)
for rule, tt, rbi, rbt in rule_rows[:limit]
]
# Project-scoped rules — verifies ownership via Project.user_id.
from scribe.models.project import Project
proj_rules_q = (
select(Rule.id, Rule.title, Rule.statement)
select(Rule)
.join(Project, Rule.project_id == Project.id)
.where(
Project.user_id == user_id,
@@ -859,11 +1214,39 @@ async def get_applicable_rules(
)
.order_by(Rule.order_index, Rule.title)
)
if reachable is not None:
proj_rules_q = proj_rules_q.where(
or_(Rule.tier == "always_on", Rule.id.in_(reachable))
)
else:
proj_rules_q = proj_rules_q.where(Rule.tier == "always_on")
proj_rule_rows = (await session.execute(proj_rules_q)).all()
project_rules = [
{"id": rid, "title": rtitle, "statement": stmt}
for rid, rtitle, stmt in proj_rule_rows
]
project_rules = [rule_brief(rule) for (rule,) in proj_rule_rows]
# Edges travel with the rules they belong to (milestone 307).
#
# A co_surfaces partner that was not otherwise selected is ADDED, because a
# rule that arrives without the half it fails with is the failure the edge
# was created to prevent. Suppressions are passed as exclusions so an
# explicit mute still wins over an edge.
surfaced_ids = [r["id"] for r in rules] + [r["id"] for r in project_rules]
partners = await co_surfaced_partners(
user_id, surfaced_ids, exclude_ids=set(suppressed_rule_ids),
)
for partner in partners:
rules.append(rule_brief(partner, via="co_surfaces"))
surfaced_ids.append(partner.id)
# Relations on every surfaced rule, so a reader can see that an override
# exists rather than discovering the contradiction by acting on the wrong
# one. Areas too — they are why a conditional rule is here at all.
edges = await list_rule_relations(surfaced_ids)
areas = await list_rule_systems(surfaced_ids)
for brief in (*rules, *project_rules):
if edges.get(brief["id"]):
brief["relations"] = edges[brief["id"]]
if areas.get(brief["id"]):
brief["systems"] = areas[brief["id"]]
return {
"rules": rules,
+91 -19
View File
@@ -14,38 +14,99 @@ from scribe.models import async_session
from scribe.models.note import Note
from scribe.models.system import RecordSystem, System
from scribe.services import access
from scribe.services import canonical_systems as canonical_systems_svc
logger = logging.getLogger(__name__)
# The standard cross-project vocabulary (#2798): names that mean the same
# thing in every project, so a starter set reads the same everywhere. The
# bootstrap ask (mcp/tools/systems) names them; the inception seed
# (services/inception, milestone 297) mints them. Charters are deliberately
# generic — a project refines them as its own records accrue.
STANDARD_SYSTEMS: tuple[tuple[str, str], ...] = (
("CI & Release", "How the project is verified and shipped: pipelines, runners, image/artifact builds, release tagging and rollback."),
("Auth & Access", "Who may do what: identity, sessions/tokens, permissions and the scoping of every read and write to the right users."),
("Data Model & Storage", "What is stored and how it is shaped: the schema, migrations, serialisation and the services that own a table's lifecycle."),
("API Surface", "The doors into the capability: HTTP routes, tool/RPC surfaces, request parsing, error envelopes and their contracts."),
("UI & Design", "What people see and touch: views, components, client state, and the design tokens/recipes they are built from."),
("Import & Export", "Data crossing the boundary: backups, exports, imports, sync with other systems, file formats."),
("Background Jobs", "Work that runs without a request: schedulers, queues, periodic ticks, retention and maintenance."),
("Observability", "How the system reports on itself: logging, metrics, audit trails, health and diagnostics."),
)
def local_name_key(name: str) -> str:
"""The within-project uniqueness key: case and spacing, nothing else.
Deliberately weaker than `canonical_slug`. This one answers "is this the
same System I already have here", where the operator's own spelling is the
thing being compared; the canonical slug answers "is this the same AREA as
some other project's System", where spelling is exactly what must be
ignored.
"""
return " ".join(name.split()).lower()
async def assess_system_name(user_id: int, project_id: int, name: str) -> dict:
"""What BOTH doors must know before minting a System name (milestone 307).
Lived in the MCP tool alone until now, which is how the web UI shipped
without a gate the agent surface enforced (#2482). One service function, so
the two doors cannot answer the same question differently (rule 33).
Returns `{"duplicate": …|None, "canonical": …|None}`:
- `duplicate` — this project already has a System by that name. A hard stop
for the caller: a second one splits the area's records across two piles.
- `canonical` — the global catalog covers this area, with a `basis`.
`exact` is mechanical and safe to apply on the spot; `overlap` is a
judgment call and must be OFFERED, never applied. Neither ever blocks:
an unmatched name is a project-specific area, which is legitimate.
Fails open on both arms — a naming aid must never break a create.
"""
out: dict = {"duplicate": None, "canonical": None}
key = local_name_key(name)
if not key:
return out
try:
for existing in await list_systems(user_id, project_id, include_archived=True):
if local_name_key(existing.name) == key:
out["duplicate"] = {"id": existing.id, "name": existing.name}
return out
except Exception:
logger.debug("system name assessment: local scan failed", exc_info=True)
return out
try:
exact = await canonical_systems_svc.find_by_name(name)
if exact is not None:
out["canonical"] = {
"id": exact.id, "name": exact.name, "basis": "exact",
}
return out
# No exact hit: fall back to the same overlap scoring the review
# surface uses, so a create-time offer and a later proposal never
# disagree about which area a name resembles.
near = await canonical_systems_svc.best_overlap(name)
if near is not None:
out["canonical"] = near
except Exception:
logger.debug("system name assessment: catalog lookup failed", exc_info=True)
return out
async def standard_systems() -> list[tuple[str, str]]:
"""The standard cross-project vocabulary (#2798) as (name, charter) pairs.
Reads the GLOBAL canonical catalog (milestone 307). This was a tuple
constant in this module until the catalog became a table: a constant
cannot be a foreign key, so nothing outside a project could reference an
area, and the list only ever applied on the inception-seed path — which is
how three spellings of "CI & Release" reached one instance anyway.
"""
return [(entry.name, entry.description or "") for entry in
await canonical_systems_svc.list_canonical_systems()]
async def seed_standard_systems(user_id: int, project_id: int) -> list[System]:
"""Mint the standard starter set for a project that has NO Systems yet
(milestone 297). Idempotent: a project with any System — the vocabulary
already started, standard or not — gets nothing; the duplicate gate and
the project's own judgment take it from there. [] without write access."""
the project's own judgment take it from there. [] without write access.
Seeded Systems are mapped to their catalog entry as they are created, so a
project born this way needs no reconciliation pass later."""
if await list_systems(user_id, project_id, include_archived=True):
return []
out: list[System] = []
for index, (name, charter) in enumerate(STANDARD_SYSTEMS):
for index, entry in enumerate(await canonical_systems_svc.list_canonical_systems()):
system = await create_system(
user_id, project_id, name, description=charter, order_index=index,
user_id, project_id, entry.name, description=entry.description,
order_index=index, canonical_id=entry.id,
)
if system is None:
break
@@ -60,8 +121,14 @@ async def create_system(
description: str | None = None,
color: str | None = None,
order_index: int = 0,
canonical_id: int | None = None,
) -> System | None:
"""Create a System. None if the user can't write the project."""
"""Create a System. None if the user can't write the project.
`canonical_id` maps the new System onto the global catalog; leaving it None
is fine — an unmapped System is fully usable, and the mapping can be
proposed later (services/canonical_systems.propose_mappings).
"""
if not await access.can_write_project(user_id, project_id):
return None
async with async_session() as session:
@@ -72,6 +139,7 @@ async def create_system(
description=description,
color=color,
order_index=order_index,
canonical_id=canonical_id,
)
session.add(system)
await session.commit()
@@ -110,6 +178,10 @@ async def list_systems(
async def update_system(user_id: int, system_id: int, **fields: object) -> System | None:
"""Update a System if the user can write its project."""
# canonical_id is deliberately NOT settable here: canonical_systems.
# set_system_canonical is its single writer, because it also validates the
# catalog entry is live. Two entry points onto one column is the drift this
# table exists to end.
allowed = {"name", "description", "color", "status", "order_index"}
async with async_session() as session:
system = await session.get(System, system_id)
+21
View File
@@ -82,3 +82,24 @@ def _no_supersession():
with patch("scribe.services.plugin_context.superseded_ids",
AsyncMock(return_value=set())):
yield
@pytest.fixture(autouse=True)
def _no_rule_arm():
"""Stub the write-path hint's standing-RULES arm (milestone 307).
Autouse, and deliberately so. The arm calls semantic_search_rules, which
loads the embedding model — so every unrelated plugin-context test that
already stubs the NOTES search would otherwise pull a real model into a
unit test through the one arm it forgot to stub. The forty-odd existing
call sites should not each have to learn about a new arm.
The arm's own behaviour is covered where it belongs: the document shape in
tests/test_services_rule_embeddings.py, the surfacing rules against real
Postgres in tests/test_integration_rule_surfacing.py, and the hook's dedup
channel in tests/test_write_path_trigger.py. A test that wants the arm
live can re-patch it.
"""
with patch("scribe.services.plugin_context.semantic_search_rules",
AsyncMock(return_value=[])):
yield
+8 -2
View File
@@ -132,7 +132,9 @@ def fake_milestone(**attrs) -> MagicMock:
def fake_system(**attrs) -> MagicMock:
return _with_defaults({"id": 1, "name": "Reader", "project_id": 5}, attrs)
return _with_defaults(
{"id": 1, "name": "Reader", "project_id": 5, "canonical_id": None}, attrs,
)
def fake_rulebook(**attrs) -> MagicMock:
@@ -151,8 +153,12 @@ def fake_topic(**attrs) -> MagicMock:
def fake_rule(**attrs) -> MagicMock:
return _with_defaults({
"id": 1, "topic_id": 10, "title": "dev is home",
"id": 1, "topic_id": 10, "project_id": None, "title": "dev is home",
"statement": "Work directly on dev", "why": "", "how_to_apply": "",
# Named for the note-2109 reason the whole helper exists: unnamed,
# `when_to_apply` and `arose_from_id` would be truthy MagicMocks and
# rule_brief would attach both keys on every stand-in.
"when_to_apply": None, "tier": "always_on", "arose_from_id": None,
"order_index": 0, "created_at": _now(), "updated_at": _now(),
}, attrs)
+18 -5
View File
@@ -57,9 +57,22 @@ def test_normalize_choices_is_canonical_and_complete():
"design_system_id": None, "seed_systems": False}
def test_standard_systems_vocabulary_is_one_list_for_ask_and_seed():
from scribe.mcp.tools.systems import _STANDARD_SYSTEMS
from scribe.services.systems import STANDARD_SYSTEMS
assert _STANDARD_SYSTEMS == tuple(n for n, _ in STANDARD_SYSTEMS)
assert len(STANDARD_SYSTEMS) == 8 and all(charter for _, charter in STANDARD_SYSTEMS)
def test_standard_systems_vocabulary_reads_the_catalog_not_a_constant():
"""The vocabulary moved from a module constant to the global catalog table
(milestone 307): a constant cannot be a foreign key, so nothing outside a
project could reference an area. The seed and the bootstrap ask must both
read the table, or the list they show and the list they mint diverge."""
import inspect
from scribe.services import systems as systems_svc
assert not hasattr(systems_svc, "STANDARD_SYSTEMS"), (
"the constant is gone — the catalog table is the single source"
)
source = inspect.getsource(systems_svc.seed_standard_systems)
assert "list_canonical_systems" in source
assert "canonical_id=entry.id" in source, (
"a seeded System must be mapped as it is created, or a project born "
"from the standard set still needs a reconciliation pass"
)
+7 -2
View File
@@ -13,6 +13,7 @@ from scribe.models.project import Project
from scribe.models.rulebook import Rulebook
from scribe.services import inception as inception_svc
from scribe.services import rulebooks as rulebooks_svc
from scribe.services import canonical_systems as canonical_svc
from scribe.services import systems as systems_svc
from tests.helpers import ensure_user
@@ -62,7 +63,11 @@ async def test_decide_applies_every_effect_and_records_last(seeded):
})
assert out["effects"]["excluded"] == [seeded["always"]]
assert out["effects"]["subscribed"] == [seeded["other"]]
assert len(out["effects"]["systems_seeded"]) == len(systems_svc.STANDARD_SYSTEMS)
catalog = await canonical_svc.list_canonical_systems()
assert len(out["effects"]["systems_seeded"]) == len(catalog)
# Seeded Systems come out mapped, not needing a later reconciliation.
seeded_systems = await systems_svc.list_systems(owner, pid)
assert all(s.canonical_id is not None for s in seeded_systems)
# The exclusion is total: the project's always-on set is empty, the
# departure is named, the subscription binds.
@@ -81,7 +86,7 @@ async def test_decide_applies_every_effect_and_records_last(seeded):
# Re-deciding with seed again mints nothing twice; include reverses the exclusion.
again = await inception_svc.decide(owner, pid, via="ui", choices={"seed_systems": True})
assert again["effects"]["systems_seeded"] == []
assert len(await systems_svc.list_systems(owner, pid)) == len(systems_svc.STANDARD_SYSTEMS)
assert len(await systems_svc.list_systems(owner, pid)) == len(catalog)
await rulebooks_svc.include_always_on_rulebook_for_project(pid, seeded["always"], owner)
assert [r.title for r in await rulebooks_svc.list_always_on_rules(owner, project_id=pid)] == ["dev is home"]
+175
View File
@@ -0,0 +1,175 @@
"""Real-Postgres tests for WHICH rules reach a session (milestone 307 step 5).
What mocks can't prove, and what this milestone must not get wrong:
1. **Nothing stops binding.** A rule with no tier, no areas and no edges
behaves exactly as it did before tiers existed. That is the one failure this
whole design must not produce, and it is asserted first.
2. A conditional rule is invisible to a project that doesn't work in its area,
and arrives — binding, not suggested — to one that does.
3. A `co_surfaces` partner arrives with its other half, which is the failure
that made merging rule 144 into rule 46 look like the only fix.
4. An explicit suppression outranks an edge.
"""
import pytest
import pytest_asyncio
from scribe.models import async_session
from scribe.models.project import Project
from scribe.models.rulebook import Rulebook
from scribe.services import canonical_systems as canonical_svc
from scribe.services import rulebooks as rulebooks_svc
from scribe.services import systems as systems_svc
from tests.helpers import ensure_user
pytestmark = [pytest.mark.integration, pytest.mark.usefixtures("_dispose_engine")]
@pytest_asyncio.fixture
async def world():
"""A project with TWO rulebooks, because the two payloads are different sets.
`list_always_on_rules` covers always-on rulebooks; `get_applicable_rules`
covers SUBSCRIBED ones. Conflating them is easy and would make these tests
assert nothing, so the fixture carries one of each and every test says
which payload it is about.
"""
async with async_session() as s:
owner = await ensure_user(s, "surfacing_owner")
project = Project(user_id=owner.id, title="Surfacing target")
s.add(project)
await s.flush()
ids = {"owner": owner.id, "pid": project.id}
await s.commit()
always = await rulebooks_svc.create_rulebook(ids["owner"], "Family standards")
async with async_session() as s:
rb = await s.get(Rulebook, always.id)
rb.always_on = True
await s.commit()
always_topic = await rulebooks_svc.create_topic(always.id, ids["owner"], "git")
await rulebooks_svc.create_rule(
always_topic.id, ids["owner"], "dev is home", "Work on dev.",
)
book = await rulebooks_svc.create_rulebook(ids["owner"], "Subscribed practices")
topic = await rulebooks_svc.create_topic(book.id, ids["owner"], "release")
plain = await rulebooks_svc.create_rule(
topic.id, ids["owner"], "Between batches, keep stacking", "Keep going.",
)
await rulebooks_svc.subscribe_project(
project_id=ids["pid"], rulebook_id=book.id, user_id=ids["owner"],
)
ids.update({
"always": always.id, "always_topic": always_topic.id,
"book": book.id, "topic": topic.id, "plain": plain.id,
})
return ids
async def _titles(ids) -> set[str]:
applicable = await rulebooks_svc.get_applicable_rules(ids["pid"], ids["owner"])
return {r["title"] for r in applicable["rules"]}
@pytest.mark.integration
async def test_a_rule_with_no_tier_no_areas_and_no_edges_binds_exactly_as_before(world):
"""THE compatibility guarantee. An install upgrades and every rule it
already had keeps arriving — no tier set, no areas, no edges, still bound.
Getting this wrong would silently stop enforcing rules people rely on,
which is worse than any amount of payload bloat."""
always_on = await rulebooks_svc.list_always_on_rules(world["owner"])
assert "dev is home" in {r.title for r in always_on}
assert "Between batches, keep stacking" in await _titles(world)
@pytest.mark.integration
async def test_a_conditional_rule_is_reachable_not_resident(world):
"""It leaves the session-start payload entirely — that is the point of the
tier — and it does NOT reach a project with no matching area."""
# In the ALWAYS-ON book: the tier alone keeps it out of the session-start
# payload, which is the whole point of the tier.
resident = await rulebooks_svc.create_rule(
world["always_topic"], world["owner"], "Release tagging", "Derive the tag.",
when_to_apply="when cutting a release", tier="conditional",
)
assert resident.tier == "conditional"
always_on = await rulebooks_svc.list_always_on_rules(world["owner"])
assert "Release tagging" not in {r.title for r in always_on}
# In the SUBSCRIBED book, untagged: the project has no area to reach it by,
# so it stays out of the project payload too. Absent for a DIFFERENT reason
# than above, which is why both are asserted.
await rulebooks_svc.create_rule(
world["topic"], world["owner"], "Untagged conditional", "No area yet.",
when_to_apply="sometime", tier="conditional",
)
assert "Untagged conditional" not in await _titles(world)
@pytest.mark.integration
async def test_a_conditional_rule_binds_a_project_that_works_in_its_area(world):
"""The payoff: the tag match carries it in deterministically. The project
reaches the area through its own System's canonical_id — its local NAME is
irrelevant, which is the whole reason the catalog exists."""
area = await canonical_svc.find_by_name("CI & Release")
assert area is not None, "migration 0087 seeds the standard vocabulary"
rule = await rulebooks_svc.create_rule(
world["topic"], world["owner"], "Release tagging", "Derive the tag.",
when_to_apply="when cutting a release", tier="conditional",
)
await rulebooks_svc.set_rule_systems(rule.id, world["owner"], [area.id])
# Still absent: the project has no Systems at all yet.
assert "Release tagging" not in await _titles(world)
# The project names the area with its OWN word, mapped to the same canon.
local = await systems_svc.create_system(
world["owner"], world["pid"], "CI & runners", description="ours",
)
await canonical_svc.set_system_canonical(world["owner"], local.id, area.id)
surfaced = await rulebooks_svc.get_applicable_rules(world["pid"], world["owner"])
hit = [r for r in surfaced["rules"] if r["title"] == "Release tagging"]
assert hit, "a tagged conditional rule must bind a project working in that area"
assert [s["name"] for s in hit[0]["systems"]] == ["CI & Release"]
@pytest.mark.integration
async def test_co_surfaces_drags_in_the_half_that_would_have_been_missed(world):
"""Rule 144 was split off rule 46 and folded back the same day because
"either rule could surface without the other". This is the edge that makes
that unnecessary: the partner arrives even though nothing else selected
it, and says why it is here."""
partner = await rulebooks_svc.create_rule(
world["topic"], world["owner"], "Version names are labels",
"A name decides nothing.",
when_to_apply="when naming a build", tier="conditional",
)
await rulebooks_svc.add_rule_relation(
world["owner"], world["plain"], partner.id, "co_surfaces",
note="they fail together",
)
surfaced = await rulebooks_svc.get_applicable_rules(world["pid"], world["owner"])
hit = [r for r in surfaced["rules"] if r["title"] == "Version names are labels"]
assert hit, "a co_surfaces partner must arrive with its other half"
assert hit[0]["via"] == "co_surfaces"
@pytest.mark.integration
async def test_a_suppression_outranks_an_edge(world):
"""The edge says these belong together; the suppression says this project
does not want that one. An explicit decision beats an inferred one."""
partner = await rulebooks_svc.create_rule(
world["topic"], world["owner"], "Muted partner", "Should not arrive.",
tier="conditional",
)
await rulebooks_svc.add_rule_relation(
world["owner"], world["plain"], partner.id, "co_surfaces",
)
await rulebooks_svc.suppress_rule_for_project(
world["pid"], partner.id, world["owner"],
)
surfaced = await rulebooks_svc.get_applicable_rules(world["pid"], world["owner"])
assert "Muted partner" not in {r["title"] for r in surfaced["rules"]}
+67 -8
View File
@@ -1,5 +1,5 @@
"""Tests for MCP rulebook tools — patches the service layer."""
from unittest.mock import AsyncMock, patch
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from tests.helpers import FakeMCP, fake_rule, fake_rulebook, fake_topic
@@ -48,11 +48,25 @@ async def test_get_rulebook_raises_when_not_found():
await get_rulebook(rulebook_id=999)
def _plain_detail():
"""Stub the rule_detail seam these tool tests are not about.
create/update/get_rule now return through services.rulebooks.rule_detail,
which reads the rule's areas and edges from the database. These are unit
tests with no database, and what they assert is that the TOOL forwards the
right arguments — so the seam is stubbed to the plain record, the same way
they already stub the create/update calls themselves.
"""
async def _detail(_uid, rule, _system_ids=None):
return rule.to_dict()
return patch("scribe.mcp.tools.rulebooks.rulebooks_svc.rule_detail", _detail)
@pytest.mark.asyncio
async def test_create_rule_passes_required_fields():
rule = fake_rule(id=100, title="r", statement="s", topic_id=10)
mock = AsyncMock(return_value=rule)
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_rule", mock):
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_rule", mock), _plain_detail():
from scribe.mcp.tools.rulebooks import create_rule
await create_rule(
topic_id=10, title="dev is home", statement="Work directly on dev",
@@ -84,7 +98,8 @@ async def test_create_rule_force_bypasses_duplicate_gate():
find_mock = AsyncMock()
with patch("scribe.mcp.tools.rulebooks.dedup_svc.find_duplicate_rule", find_mock), \
patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_rule",
AsyncMock(return_value=fake_rule(id=5, title="r", statement="s", topic_id=10))):
AsyncMock(return_value=fake_rule(id=5, title="r", statement="s", topic_id=10))), \
_plain_detail():
from scribe.mcp.tools.rulebooks import create_rule
out = await create_rule(topic_id=10, title="dev is home", statement="x", force=True)
assert out["id"] == 5
@@ -95,7 +110,7 @@ async def test_create_rule_force_bypasses_duplicate_gate():
async def test_update_rule_only_sends_non_default_fields():
rule = fake_rule(id=100, title="r", statement="s", topic_id=10)
mock = AsyncMock(return_value=rule)
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.update_rule", mock):
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.update_rule", mock), _plain_detail():
from scribe.mcp.tools.rulebooks import update_rule
await update_rule(rule_id=1, statement="new statement")
args, kwargs = mock.call_args
@@ -169,7 +184,7 @@ def test_register_attaches_all_sixteen_tools():
mcp = FakeMCP()
register(mcp)
assert len(mcp.names) == 24 # +exclude/include_always_on_rulebook (milestone 297)
assert len(mcp.names) == 26 # +relate_rules/unrelate_rules (milestone 307)
# spot-check a few names
assert "list_rulebooks" in mcp.names
assert "create_rule" in mcp.names
@@ -239,7 +254,7 @@ async def test_update_rulebook_omits_always_on_when_none():
async def test_create_project_rule_passes_required_fields():
rule = fake_rule(id=100, title="r", statement="s", topic_id=10)
mock = AsyncMock(return_value=rule)
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_project_rule", mock):
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_project_rule", mock), _plain_detail():
from scribe.mcp.tools.rulebooks import create_project_rule
await create_project_rule(
project_id=42,
@@ -257,7 +272,7 @@ async def test_create_project_rule_passes_required_fields():
async def test_create_project_rule_derives_title_from_statement():
rule = fake_rule(id=100, title="r", statement="s", topic_id=10)
mock = AsyncMock(return_value=rule)
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_project_rule", mock):
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_project_rule", mock), _plain_detail():
from scribe.mcp.tools.rulebooks import create_project_rule
await create_project_rule(
project_id=42,
@@ -272,7 +287,7 @@ async def test_create_project_rule_derives_title_from_statement():
async def test_create_project_rule_uses_explicit_title_when_given():
rule = fake_rule(id=100, title="r", statement="s", topic_id=10)
mock = AsyncMock(return_value=rule)
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_project_rule", mock):
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.create_project_rule", mock), _plain_detail():
from scribe.mcp.tools.rulebooks import create_project_rule
await create_project_rule(
project_id=42,
@@ -325,3 +340,47 @@ async def test_unsuppress_topic_for_project_passes_through():
kwargs = mock.call_args.kwargs
assert kwargs == {"project_id": 3, "topic_id": 22, "user_id": 7}
assert out == {"project_id": 3, "topic_id": 22, "suppressed": False}
# ── Typed edges between rules (milestone 307) ───────────────────────────
@pytest.mark.asyncio
async def test_relate_rules_forwards_the_kind_and_the_why():
"""The edge exists so a shape stops being merged into one row. The `note`
travels with it for the same reason a rule carries `why`: whoever later
decides whether the edge still holds needs the reasoning."""
relation = MagicMock()
relation.to_dict.return_value = {"id": 9, "kind": "co_surfaces"}
mock = AsyncMock(return_value=relation)
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.add_rule_relation", mock):
from scribe.mcp.tools.rulebooks import relate_rules
out = await relate_rules(
from_rule_id=46, to_rule_id=144, kind="co_surfaces",
note="a stale channel tag and an unparseable version both read as "
"no update available",
)
assert out["id"] == 9
args = mock.call_args.args
assert args[0] == 7 and args[1] == 46 and args[2] == 144
assert args[3] == "co_surfaces"
assert "no update available" in args[4]
@pytest.mark.asyncio
async def test_relate_rules_raises_when_either_end_is_not_yours():
"""The service returns None when it cannot see both rules — a one-sided
edge would surface a rule the caller has no business reading."""
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.add_rule_relation",
AsyncMock(return_value=None)):
from scribe.mcp.tools.rulebooks import relate_rules
with pytest.raises(ValueError, match="not found"):
await relate_rules(from_rule_id=1, to_rule_id=2, kind="overrides")
@pytest.mark.asyncio
async def test_unrelate_rules_raises_when_the_edge_is_gone():
with patch("scribe.mcp.tools.rulebooks.rulebooks_svc.remove_rule_relation",
AsyncMock(return_value=False)):
from scribe.mcp.tools.rulebooks import unrelate_rules
with pytest.raises(ValueError, match="not found"):
await unrelate_rules(relation_id=99)
+93 -27
View File
@@ -5,26 +5,86 @@ import pytest
from tests.helpers import fake_note, fake_system
# The name assessment both doors run before minting (milestone 307). A test
# that patches systems_svc wholesale must stub it, or the awaited MagicMock
# raises — this shape is the "nothing matched" answer.
_NO_MATCH = {"duplicate": None, "canonical": None}
@pytest.mark.asyncio
async def test_create_system_returns_dict():
with patch("scribe.mcp.tools.systems.current_user_id", return_value=1), \
patch("scribe.mcp.tools.systems.systems_svc") as svc:
svc.assess_system_name = AsyncMock(return_value=_NO_MATCH)
svc.create_system = AsyncMock(return_value=fake_system(name="Reader"))
from scribe.mcp.tools.systems import create_system
result = await create_system(project_id=5, name="Reader", description="pdf reader")
assert result["name"] == "Reader"
# An unmatched name is a project-specific area: created, no offer, no fuss.
assert "canonical_suggestion" not in result and "canonical_note" not in result
@pytest.mark.asyncio
async def test_create_system_no_access_raises():
with patch("scribe.mcp.tools.systems.current_user_id", return_value=1), \
patch("scribe.mcp.tools.systems.systems_svc") as svc:
svc.assess_system_name = AsyncMock(return_value=_NO_MATCH)
svc.create_system = AsyncMock(return_value=None)
from scribe.mcp.tools.systems import create_system
with pytest.raises(ValueError):
await create_system(project_id=5, name="Reader")
@pytest.mark.asyncio
async def test_create_system_applies_an_exact_area_and_offers_a_similar_one():
"""The two bases must behave differently, and this is where it is decided.
`exact` differs from the catalog name only in spelling, so it is APPLIED —
that is the mechanical case the catalog exists to collapse. `overlap` is a
judgment call, so it is only OFFERED: applying it silently is how a
cross-project rule ends up surfacing in the wrong project.
"""
from scribe.mcp.tools.systems import create_system
with patch("scribe.mcp.tools.systems.current_user_id", return_value=1), \
patch("scribe.mcp.tools.systems.systems_svc") as svc:
svc.assess_system_name = AsyncMock(return_value={
"duplicate": None,
"canonical": {"id": 3, "name": "CI & Release", "basis": "exact"},
})
svc.create_system = AsyncMock(return_value=fake_system(name="CI and Release"))
exact = await create_system(project_id=5, name="CI and Release")
assert svc.create_system.await_args.kwargs["canonical_id"] == 3
assert "canonical_note" in exact and "canonical_suggestion" not in exact
with patch("scribe.mcp.tools.systems.current_user_id", return_value=1), \
patch("scribe.mcp.tools.systems.systems_svc") as svc:
svc.assess_system_name = AsyncMock(return_value={
"duplicate": None,
"canonical": {"id": 3, "name": "CI & Release", "basis": "overlap", "score": 0.33},
})
svc.create_system = AsyncMock(return_value=fake_system(id=9, name="CI & runners"))
similar = await create_system(project_id=5, name="CI & runners")
assert svc.create_system.await_args.kwargs["canonical_id"] is None
assert similar["canonical_suggestion"]["id"] == 3
assert "map_system_to_canonical(9, 3)" in similar["canonical_suggestion"]["message"]
@pytest.mark.asyncio
async def test_create_system_duplicate_names_the_existing_one_and_creates_nothing():
from scribe.mcp.tools.systems import create_system
with patch("scribe.mcp.tools.systems.current_user_id", return_value=1), \
patch("scribe.mcp.tools.systems.systems_svc") as svc:
svc.assess_system_name = AsyncMock(return_value={
"duplicate": {"id": 4, "name": "Reader"}, "canonical": None,
})
svc.create_system = AsyncMock()
result = await create_system(project_id=5, name="reader")
assert result["duplicate"] is True and result["existing_id"] == 4
assert "Reader" in result["message"]
svc.create_system.assert_not_awaited()
@pytest.mark.asyncio
async def test_get_system_splits_records_by_kind():
issue = MagicMock(); issue.to_dict.return_value = {"id": 10}; issue.task_kind = "issue"; issue.status = "todo"
@@ -113,6 +173,15 @@ async def test_untagged_hint_escalates_in_a_mature_zero_systems_project():
patch("scribe.mcp.tools.systems.notes_svc") as notes:
svc.list_systems = AsyncMock(return_value=[])
notes.list_notes = AsyncMock(return_value=(recent, 282))
# The standard names come from the GLOBAL catalog now (milestone 307),
# not a module constant — so the ask reads them through the service.
# That the SEEDED vocabulary is these eight is migration 0087's
# business, asserted against a real database in the inception
# integration test; what belongs here is that whatever the catalog
# holds reaches the ask verbatim.
svc.standard_systems = AsyncMock(return_value=[
("CI & Release", "..."), ("Auth & Access", "..."),
])
hint = await untagged_systems_hint(1, 5)
assert "282 records" in hint
assert "Fix scrape retry backoff" in hint # the project's own evidence
@@ -126,6 +195,25 @@ async def test_untagged_hint_escalates_in_a_mature_zero_systems_project():
assert "no Systems yet" not in hint
@pytest.mark.asyncio
async def test_bootstrap_ask_still_asks_when_the_catalog_is_unreachable():
"""The standard names are an AID to the question, not the question. If the
catalog read fails (or an install has an empty one), the ask must still
carry the project's evidence and demand the same deliverable — degrading to
a weaker nudge is acceptable, going silent is not."""
from scribe.mcp.tools.systems import untagged_systems_hint
recent = [fake_note(title="Fix scrape retry backoff")]
with patch("scribe.mcp.tools.systems.systems_svc") as svc, \
patch("scribe.mcp.tools.systems.notes_svc") as notes:
svc.list_systems = AsyncMock(return_value=[])
notes.list_notes = AsyncMock(return_value=(recent, 282))
svc.standard_systems = AsyncMock(side_effect=RuntimeError("db down"))
hint = await untagged_systems_hint(1, 5)
assert hint is not None
assert "282 records" in hint and "create_system" in hint
assert "3-6" in hint and "without asking permission" in hint
@pytest.mark.asyncio
async def test_bootstrap_ask_stays_quiet_below_threshold_and_fails_open():
from scribe.mcp.tools import systems as tools
@@ -155,33 +243,11 @@ async def test_populated_vocabulary_never_counts_records():
notes.list_notes.assert_not_awaited()
@pytest.mark.asyncio
async def test_create_system_same_normalized_name_is_duplicate_gated():
existing = fake_system(id=7, name="Scrape Pipeline")
existing.id = 7
existing.name = "Scrape Pipeline"
with patch("scribe.mcp.tools.systems.current_user_id", return_value=1), \
patch("scribe.mcp.tools.systems.systems_svc") as svc:
svc.list_systems = AsyncMock(return_value=[existing])
svc.create_system = AsyncMock()
from scribe.mcp.tools.systems import create_system
result = await create_system(project_id=5, name=" scrape pipeline ")
assert result["duplicate"] is True
assert result["existing_id"] == 7
svc.create_system.assert_not_awaited()
@pytest.mark.asyncio
async def test_create_system_distinct_name_passes_the_gate():
other = fake_system(id=7, name="Workers")
other.name = "Workers"
with patch("scribe.mcp.tools.systems.current_user_id", return_value=1), \
patch("scribe.mcp.tools.systems.systems_svc") as svc:
svc.list_systems = AsyncMock(return_value=[other])
svc.create_system = AsyncMock(return_value=fake_system(id=8, name="Exporter"))
from scribe.mcp.tools.systems import create_system
result = await create_system(project_id=5, name="Exporter")
assert result["name"] == "Exporter"
# The name gate's own cases (case/whitespace normalisation, exact-over-overlap,
# fail-open) moved to tests/test_services_systems.py with the logic itself —
# services/systems.assess_system_name, so both doors share one answer (#2482).
# What stays the TOOL's job — rendering a duplicate, applying an exact area,
# offering an overlap — is covered at the top of this file.
@pytest.mark.asyncio
+4 -1
View File
@@ -44,7 +44,8 @@ def test_service_signatures_require_user_id():
"create_rulebook", "list_rulebooks", "get_rulebook",
"update_rulebook", "delete_rulebook", "find_rulebook_by_title",
"create_topic", "list_topics", "get_topic", "update_topic", "delete_topic",
"create_rule", "create_project_rule",
"create_rule", "create_project_rule", "rule_detail",
"set_rule_systems", "add_rule_relation", "remove_rule_relation",
"list_rules", "list_always_on_rules",
"get_rule", "update_rule", "delete_rule",
"subscribe_project", "unsubscribe_project", "get_applicable_rules",
@@ -117,5 +118,7 @@ def test_rule_and_subscription_handlers_callable():
for name in (
"list_rules", "create_rule", "get_rule", "update_rule", "delete_rule",
"subscribe_project", "unsubscribe_project", "get_project_rules",
# The typed edges — both doors carry them (rule 33).
"relate_rules", "unrelate_rules",
):
assert callable(getattr(rb_routes, name))
+64
View File
@@ -0,0 +1,64 @@
"""The canonical-slug matcher — the line between what maps mechanically and
what a human is asked to confirm (milestone 307, note 3026).
These cases are the real drift found across the author's own instance: one area
carrying three spellings, and two areas that LOOK alike and are not the same.
Getting the boundary wrong in either direction is a silent failure — a missed
mapping nobody thinks to make again, or a cross-project record surfacing in the
wrong project.
"""
import pytest
from scribe.services.canonical_systems import canonical_slug
@pytest.mark.parametrize("name", ["CI & Release", "CI and Release", "CI & release",
" ci and release "])
def test_spelling_variants_of_one_area_collapse_to_one_key(name):
"""Case, spacing, punctuation and "&" vs "and" are not real differences.
All three of the first spellings were live in different projects at once."""
assert canonical_slug(name) == "ci-and-release"
@pytest.mark.parametrize("name,expected", [
("Auth & Access", "auth-and-access"),
("Data Model & Storage", "data-model-and-storage"),
("UI & Design", "ui-and-design"),
("Background Jobs", "background-jobs"),
("Observability", "observability"),
])
def test_the_seeded_vocabulary_slugs_match_the_migration(name, expected):
"""Migration 0087 writes these slugs literally. If the function and the
migration disagree, every seeded entry becomes unreachable by exact match
and every mapping silently degrades to a proposal."""
assert canonical_slug(name) == expected
@pytest.mark.parametrize("a,b", [
("CI & Release", "CI & runners"),
("Auth & Access", "Auth & Accounts"),
("UI & Design", "Frontend (Vue app)"),
("UI & Design", "Web Shell and Theme"),
])
def test_genuinely_different_names_do_not_collapse(a, b):
"""These pairs may or may not be the same area — that is a judgment call,
so they must NOT map automatically. They reach the operator as proposals."""
assert canonical_slug(a) != canonical_slug(b)
def test_a_nameless_system_yields_no_key():
"""An empty slug is the one value callers must special-case: two unnameable
Systems must not map onto each other. Both propose_mappings and find_by_name
bail on a falsy slug for this reason."""
assert canonical_slug("") == ""
assert canonical_slug(" ") == ""
assert canonical_slug("---") == ""
def test_a_punctuation_separator_is_not_read_as_the_word_and():
""""CI/Release" is a real spelling and it does NOT collapse onto
"CI & Release" — only "&" carries that meaning. It still reaches the
operator through the overlap path, where both words match; what it must not
do is map itself silently."""
assert canonical_slug("CI/Release") == "ci-release"
assert canonical_slug("CI/Release") != canonical_slug("CI & Release")
+84
View File
@@ -0,0 +1,84 @@
"""The document a rule is EMBEDDED as (milestone 307 step 4, note 3026).
This shape is measured, not chosen. Note 2485 probed the live corpus and found
the snippet was the only discriminative record in it — a 0.153 top-to-second
gap against 0.010-0.023 for everything else — and that the cause was its shape:
purpose stated twice in a short, single-topic document. These cases pin that
recipe onto rules, and pin the exclusion that matters more than any of it.
"""
import pytest
from scribe.services.embeddings import chunk_document, rule_document
def test_the_trigger_appears_twice_which_is_what_makes_a_vector_sharp():
"""Repetition of purpose + brevity is the measured cause of the snippet's
separation. The rule document reproduces it exactly: the trigger in the
title, and again as the body's first line."""
title, body = rule_document(
"Release — never without explicit request",
"Never cut a release without the operator explicitly asking.",
"before cutting any release",
)
assert title == "Release — never without explicit request — before cutting any release"
assert body.startswith("When to apply: before cutting any release")
assert "Never cut a release" in body
def test_why_is_never_embedded():
"""The exclusion this whole design turns on. `why` is dated incident
narrative — rule 46's runs to 4,300 characters — and long multi-topic prose
is what made sixteen dev-logs mutually indistinguishable: the average lands
on a centroid they all share. Adding it would not give the vector more to
work with; it would give every rule the SAME thing to work with.
rule_document takes no `why` parameter at all, which is the strongest form
of this guarantee: it cannot be passed in by a caller who means well.
"""
import inspect
assert "why" not in inspect.signature(rule_document).parameters
def test_a_rule_with_no_trigger_still_embeds_just_less_sharply():
"""Every rule written before milestone 307 has no trigger. Degrading to
title + statement keeps them findable; it does NOT pad the document with
whatever text is lying around, which would be the tempting fix and the
wrong one."""
title, body = rule_document("dev is home", "Work directly on dev.", "")
assert title == "dev is home"
assert body == "Work directly on dev."
assert "When to apply" not in body
def test_an_empty_rule_yields_no_document_and_therefore_no_vector():
"""Callers gate on falsiness to skip embedding — the same contract
chunk_document has, so an emptied record stops being findable by its old
content rather than keeping a stale vector."""
assert rule_document("", "", "") == (None, None)
assert chunk_document(*rule_document("", "", "")) == []
def test_a_long_rule_chunks_and_every_chunk_carries_the_trigger():
"""Rule 46's statement is ~3,600 characters across two headed sections.
The existing chunker splits it at headings and prefixes each chunk with the
title — which now CONTAINS the trigger, so each half stays anchored to what
the rule is for. This is why splitting a merged rule costs nothing at
retrieval time."""
statement = (
"## The tags\n\n" + ("Four tags, four jobs. " * 60)
+ "\n\n## The artifact's own version\n\n" + ("Two version values. " * 60)
)
title, body = rule_document("Versioning", statement, "when cutting a release")
chunks = chunk_document(title, body)
assert len(chunks) > 1
assert all("when cutting a release" in chunk for chunk in chunks)
@pytest.mark.parametrize("trigger,expected_title", [
("before any git push", "dev is home — before any git push"),
(" before any git push ", "dev is home — before any git push"),
])
def test_the_trigger_is_trimmed_before_it_reaches_the_vector(trigger, expected_title):
title, _ = rule_document("dev is home", "Work on dev.", trigger)
assert title == expected_title
+95 -14
View File
@@ -2,6 +2,7 @@
Mirrors the pattern in tests/test_events_service.py.
"""
from datetime import datetime, timezone
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
@@ -197,6 +198,25 @@ def _empty():
return r
def _no_edges():
"""Silence the three post-query lookups get_applicable_rules now makes.
They are separate service functions with their own coverage (and the real
wiring is proven against Postgres in test_integration_rule_surfacing), so
stubbing them here keeps each of these tests about the one projection it
was written to check — rather than about the order a mocked session's
execute() calls happen to arrive in.
"""
return (
patch("scribe.services.rulebooks.co_surfaced_partners",
AsyncMock(return_value=[])),
patch("scribe.services.rulebooks.list_rule_relations",
AsyncMock(return_value={})),
patch("scribe.services.rulebooks.list_rule_systems",
AsyncMock(return_value={})),
)
@pytest.mark.asyncio
async def test_get_applicable_rules_returns_shape():
"""get_applicable_rules returns the full projection — including the
@@ -206,16 +226,20 @@ async def test_get_applicable_rules_returns_shape():
sub_result.all.return_value = [(1, "FabledSword family")]
rules_result = MagicMock()
rules_result.all.return_value = [
# (rule_id, title, statement, topic_id, topic_title, rulebook_id, rulebook_title)
(i, f"Rule {i}", f"Statement {i}", 2, "git-workflow", 1, "FabledSword family")
# The query selects the ENTITY plus three labels, so rule_brief stays
# the one place deciding what a surfaced rule carries (note 3026).
(fake_rule(id=i, title=f"Rule {i}", statement=f"Statement {i}", topic_id=2),
"git-workflow", 1, "FabledSword family")
for i in range(50)
]
# Execute order: sub_q, suppressed_rules_q, suppressed_topics_q, rules_q, proj_rules_q
# Execute order: sub_q, suppressed_rules_q, suppressed_topics_q,
# project-areas_q (milestone 307), rules_q, proj_rules_q
mock_session.execute = AsyncMock(side_effect=[
sub_result, _empty(), _empty(), rules_result, _empty(),
sub_result, _empty(), _empty(), _empty(), rules_result, _empty(),
])
with patch("scribe.services.rulebooks.async_session") as mock_cls:
_p1, _p2, _p3 = _no_edges()
with patch("scribe.services.rulebooks.async_session") as mock_cls, _p1, _p2, _p3:
mock_cls.return_value = mock_session
from scribe.services.rulebooks import get_applicable_rules
result = await get_applicable_rules(project_id=3, user_id=7, limit=50)
@@ -244,13 +268,14 @@ async def test_get_applicable_rules_truncates_when_over_limit():
sub_result.all.return_value = []
rules_result = MagicMock()
rules_result.all.return_value = [
(i, f"r{i}", "stmt", 2, "topic", 1, "rb") for i in range(51)
(fake_rule(id=i, title=f"r{i}"), "topic", 1, "rb") for i in range(51)
]
mock_session.execute = AsyncMock(side_effect=[
sub_result, _empty(), _empty(), rules_result, _empty(),
sub_result, _empty(), _empty(), _empty(), rules_result, _empty(),
])
with patch("scribe.services.rulebooks.async_session") as mock_cls:
_p1, _p2, _p3 = _no_edges()
with patch("scribe.services.rulebooks.async_session") as mock_cls, _p1, _p2, _p3:
mock_cls.return_value = mock_session
from scribe.services.rulebooks import get_applicable_rules
result = await get_applicable_rules(project_id=3, user_id=7, limit=50)
@@ -265,14 +290,17 @@ async def test_get_applicable_rules_includes_project_scoped_rules():
mock_session = make_mock_session()
proj_rules_result = MagicMock()
proj_rules_result.all.return_value = [
(100, "Use alembic", "Always run migrations via alembic, never raw SQL."),
(101, "PR-bound", "Land schema changes in their own PR."),
(fake_rule(id=100, topic_id=None, project_id=3, title="Use alembic",
statement="Always run migrations via alembic, never raw SQL."),),
(fake_rule(id=101, topic_id=None, project_id=3, title="PR-bound",
statement="Land schema changes in their own PR."),),
]
mock_session.execute = AsyncMock(side_effect=[
_empty(), _empty(), _empty(), _empty(), proj_rules_result,
_empty(), _empty(), _empty(), _empty(), _empty(), proj_rules_result,
])
with patch("scribe.services.rulebooks.async_session") as mock_cls:
_p1, _p2, _p3 = _no_edges()
with patch("scribe.services.rulebooks.async_session") as mock_cls, _p1, _p2, _p3:
mock_cls.return_value = mock_session
from scribe.services.rulebooks import get_applicable_rules
result = await get_applicable_rules(project_id=3, user_id=7)
@@ -298,10 +326,14 @@ async def test_get_applicable_rules_surfaces_suppressed_with_context():
(22, "design-system", 1, "FabledSword family"),
]
mock_session.execute = AsyncMock(side_effect=[
_empty(), suppressed_rules_result, suppressed_topics_result, _empty(), _empty(),
# sub_q, suppressed_rules_q, suppressed_topics_q, project-areas_q,
# rules_q, proj_rules_q
_empty(), suppressed_rules_result, suppressed_topics_result,
_empty(), _empty(), _empty(),
])
with patch("scribe.services.rulebooks.async_session") as mock_cls:
_p1, _p2, _p3 = _no_edges()
with patch("scribe.services.rulebooks.async_session") as mock_cls, _p1, _p2, _p3:
mock_cls.return_value = mock_session
from scribe.services.rulebooks import get_applicable_rules
result = await get_applicable_rules(project_id=3, user_id=7)
@@ -311,3 +343,52 @@ async def test_get_applicable_rules_surfaces_suppressed_with_context():
assert result["suppressed_rules"][0]["rulebook_title"] == "FabledSword family"
assert len(result["suppressed_topics"]) == 1
assert result["suppressed_topics"][0]["title"] == "design-system"
# ── rule_brief + tier (milestone 307) ───────────────────────────────────
def test_rule_brief_carries_age_but_not_the_deep_fields():
"""The shape a SURFACED rule takes, and the reason it exists.
There were three hand-written copies of this dict and they had already
diverged — none carried the timestamps the model has always held, which is
why a rule written before the capability it duplicates was
indistinguishable at read time from one still doing work (note 3026).
"""
from scribe.services.rulebooks import rule_brief
out = rule_brief(fake_rule(
when_to_apply="before any git push",
updated_at=datetime(2026, 6, 1, 14, 30, tzinfo=timezone.utc),
))
assert out["when_to_apply"] == "before any git push"
assert out["tier"] == "always_on"
# A DATE, not a stamp: the question is "how old is this", and a full ISO
# string across the always-on set is ~2k characters of payload.
assert out["updated_at"] == "2026-06-01"
# The depth stays with get_rule — putting it in every listing is the bloat
# this milestone is about.
assert "why" not in out and "how_to_apply" not in out
def test_rule_brief_omits_keys_a_rule_has_no_value_for():
"""#2483: a null key reads as a capability the record has and isn't using,
which is a different claim from not having one."""
from scribe.services.rulebooks import rule_brief
out = rule_brief(fake_rule())
assert "when_to_apply" not in out
assert "arose_from_id" not in out
def test_an_unknown_tier_falls_back_to_binding():
"""The asymmetry that decides the direction: a rule that preloads when it
needn't costs context; a rule that quietly stops preloading costs the
behaviour it was written for. So a typo binds."""
from scribe.services.rulebooks import _valid_tier
assert _valid_tier("conditional") == "conditional"
assert _valid_tier("always_on") == "always_on"
assert _valid_tier("Conditional") == "always_on"
assert _valid_tier("") == "always_on"
assert _valid_tier("occasionally") == "always_on"
+67
View File
@@ -59,3 +59,70 @@ async def test_count_open_issues_denied_returns_zero():
from scribe.services.systems import count_open_issues
result = await count_open_issues(user_id=1, project_id=5)
assert result == 0
# ── assess_system_name — the one gate both doors call (milestone 307) ──
@pytest.mark.asyncio
async def test_assess_matches_an_existing_system_on_case_and_spacing():
"""The local gate compares the operator's own spelling: case and runs of
whitespace are not a different System. Anything stronger belongs to the
CANONICAL slug, which is a different question (is this the same AREA as
another project's System) with a different answer."""
existing = MagicMock()
existing.id, existing.name = 7, "Scrape Pipeline"
with patch("scribe.services.systems.list_systems", AsyncMock(return_value=[existing])):
from scribe.services.systems import assess_system_name
out = await assess_system_name(1, 5, " scrape pipeline ")
assert out["duplicate"] == {"id": 7, "name": "Scrape Pipeline"}
# A duplicate short-circuits: there is nothing to file when nothing is created.
assert out["canonical"] is None
@pytest.mark.asyncio
async def test_assess_prefers_an_exact_area_over_a_merely_similar_one():
from scribe.services.systems import assess_system_name
exact = MagicMock()
exact.id, exact.name = 3, "CI & Release"
with patch("scribe.services.systems.list_systems", AsyncMock(return_value=[])), \
patch("scribe.services.systems.canonical_systems_svc") as canon:
canon.find_by_name = AsyncMock(return_value=exact)
canon.best_overlap = AsyncMock()
out = await assess_system_name(1, 5, "CI and Release")
assert out["canonical"] == {"id": 3, "name": "CI & Release", "basis": "exact"}
# An exact hit is the answer — no need to go looking for a lesser one.
canon.best_overlap.assert_not_awaited()
@pytest.mark.asyncio
async def test_assess_falls_back_to_overlap_and_never_invents_a_match():
from scribe.services.systems import assess_system_name
near = {"id": 3, "name": "CI & Release", "basis": "overlap", "score": 0.33}
with patch("scribe.services.systems.list_systems", AsyncMock(return_value=[])), \
patch("scribe.services.systems.canonical_systems_svc") as canon:
canon.find_by_name = AsyncMock(return_value=None)
canon.best_overlap = AsyncMock(return_value=near)
assert (await assess_system_name(1, 5, "CI & runners"))["canonical"] == near
canon.best_overlap = AsyncMock(return_value=None)
# Nothing resembles it: a project-specific area, and silence is the
# right answer — unmapped is a valid resting state.
assert (await assess_system_name(1, 5, "Soundboard"))["canonical"] is None
@pytest.mark.asyncio
async def test_assess_fails_open_so_a_naming_aid_cannot_block_a_create():
"""Both arms degrade to "no opinion" rather than raising. A create must
never fail because the catalog was unreachable."""
from scribe.services.systems import assess_system_name
with patch("scribe.services.systems.list_systems", AsyncMock(side_effect=RuntimeError("db down"))):
assert await assess_system_name(1, 5, "Reader") == {"duplicate": None, "canonical": None}
with patch("scribe.services.systems.list_systems", AsyncMock(return_value=[])), \
patch("scribe.services.systems.canonical_systems_svc") as canon:
canon.find_by_name = AsyncMock(side_effect=RuntimeError("db down"))
assert (await assess_system_name(1, 5, "Reader"))["canonical"] is None
@pytest.mark.asyncio
async def test_assess_says_nothing_about_a_nameless_system():
from scribe.services.systems import assess_system_name
assert await assess_system_name(1, 5, " ") == {"duplicate": None, "canonical": None}
+17
View File
@@ -1435,3 +1435,20 @@ async def test_the_write_time_divergence_check_is_named_in_band():
out = await pc.build_write_path_hint(1, "x.py", code=REAL_CODE, stamp_shapes=[("sym", "f")])
check.assert_not_awaited()
assert out["divergence"] == []
def test_hook_keeps_the_rule_channel_apart_from_the_other_three():
"""Milestone 307's arm, pinned the way #2708's was.
Standing rules dedup on their OWN file and their OWN query parameter. One
shared channel is the bug #2708 already fixed once: a hint of one class
silencing a different class that had never been shown. A rule named early
must not be re-offered on every later write, and must not silence — or be
silenced by — a snippet suggestion.
"""
src = HOOK.read_text()
assert ".rules.ids" in src # its own state file
assert "exclude_rule_ids=" in src # its own query channel
assert "(.rule_ids // [])[]?" in src # its own write-back
# And it rides the same request as the rest, not a second round trip.
assert "${rule_exclude_q}" in src