knox/internal/db/schema.go

package db

const Schema = `
-- IMMUTABLE LOG: every observation is append-only, never mutated
CREATE TABLE IF NOT EXISTS observations (
    id               INTEGER PRIMARY KEY AUTOINCREMENT,
    fingerprint      TEXT NOT NULL,
    source_id        TEXT NOT NULL,
    source_path      TEXT,
    project          TEXT,
    content_type     TEXT,
    title            TEXT,
    summary          TEXT,
    collected_at     TEXT NOT NULL DEFAULT (datetime('now')),
    created_at       TEXT,
    line_start       INTEGER,
    line_end         INTEGER,
    confidence       REAL DEFAULT 0.5,
    ingester_version TEXT DEFAULT '1',
    trigger          TEXT,
    provenance       TEXT DEFAULT '{}',
    node_id          TEXT NOT NULL DEFAULT '',
    hcl              INTEGER,
    received_at      TEXT
);

CREATE INDEX IF NOT EXISTS idx_obs_fingerprint ON observations(fingerprint);
CREATE INDEX IF NOT EXISTS idx_obs_collected   ON observations(collected_at);
CREATE INDEX IF NOT EXISTS idx_obs_created     ON observations(created_at);
CREATE INDEX IF NOT EXISTS idx_obs_source      ON observations(source_id, source_path);
CREATE INDEX IF NOT EXISTS idx_obs_project     ON observations(project);
CREATE INDEX IF NOT EXISTS idx_obs_trigger     ON observations(trigger);

-- MATERIALIZED CACHE: current state, reconstructable from observations
CREATE TABLE IF NOT EXISTS entries (
    fingerprint  TEXT PRIMARY KEY,
    source_id    TEXT NOT NULL,
    source_path  TEXT,
    project      TEXT,
    content_type TEXT,
    title        TEXT,
    summary      TEXT,
    first_seen   TEXT,
    last_seen    TEXT,
    ref_count    INTEGER DEFAULT 1,
    last_confidence REAL DEFAULT 0.5
);

CREATE INDEX IF NOT EXISTS idx_entries_project  ON entries(project);
CREATE INDEX IF NOT EXISTS idx_entries_source   ON entries(source_id);
CREATE INDEX IF NOT EXISTS idx_entries_seen     ON entries(last_seen);

-- PROVENANCE LINKS: multi-hop lineage between entries
CREATE TABLE IF NOT EXISTS provenance_links (
    id               INTEGER PRIMARY KEY AUTOINCREMENT,
    descendant_fp    TEXT NOT NULL,
    ancestor_fp      TEXT NOT NULL,
    hop_distance     INTEGER NOT NULL,
    relation         TEXT NOT NULL,
    created_at       TEXT DEFAULT (datetime('now'))
);

CREATE INDEX IF NOT EXISTS idx_pl_descendant ON provenance_links(descendant_fp);
CREATE INDEX IF NOT EXISTS idx_pl_ancestor   ON provenance_links(ancestor_fp);

-- REFLECTION STATE: per-session tracking
CREATE TABLE IF NOT EXISTS sessions (
    session_id  TEXT PRIMARY KEY,
    project     TEXT,
    title       TEXT,
    status      TEXT DEFAULT 'active',
    agent_count INTEGER DEFAULT 0,
    started_at  TEXT,
    ended_at    TEXT,
    last_seen   TEXT DEFAULT (datetime('now')),
    indexed     INTEGER DEFAULT 0
);

-- SOURCE REGISTRY
CREATE TABLE IF NOT EXISTS sources (
    id          TEXT PRIMARY KEY,
    name        TEXT NOT NULL,
    enabled     INTEGER DEFAULT 1,
    last_event  TEXT,
    created_at  TEXT DEFAULT (datetime('now'))
);

INSERT OR IGNORE INTO sources (id, name) VALUES ('opencode-session', 'Opencode Session Diffs');
INSERT OR IGNORE INTO sources (id, name) VALUES ('opencode-log',      'Opencode Log Files');
INSERT OR IGNORE INTO sources (id, name) VALUES ('git',               'Git History');
INSERT OR IGNORE INTO sources (id, name) VALUES ('filesystem',        'File System Watcher');

-- KNOWLEDGE THREADS: why observations exist, what questions they answer
CREATE TABLE IF NOT EXISTS threads (
    id          INTEGER PRIMARY KEY AUTOINCREMENT,
    title       TEXT NOT NULL,
    motivation  TEXT,
    status      TEXT DEFAULT 'active',
    priority    TEXT DEFAULT 'medium',
    created_at  TEXT DEFAULT (datetime('now')),
    updated_at  TEXT DEFAULT (datetime('now')),
    resolved_at TEXT,
    tags        TEXT DEFAULT '[]',
    provenance  TEXT DEFAULT '{}',
    cluster_key TEXT
);

CREATE UNIQUE INDEX IF NOT EXISTS idx_threads_cluster ON threads(cluster_key) WHERE cluster_key IS NOT NULL AND cluster_key != '';

-- SETTINGS: key-value store for runtime configuration
CREATE TABLE IF NOT EXISTS settings (
    key   TEXT PRIMARY KEY,
    value TEXT
);

-- PEERS: other knox nodes known to this one (gossip ring)
CREATE TABLE IF NOT EXISTS peers (
    peer_id        TEXT PRIMARY KEY,       -- remote node_id
    addr           TEXT,                   -- e.g. http://192.168.1.20:8931
    name           TEXT,
    last_handshake TEXT,
    cursor         INTEGER DEFAULT 0,      -- remote's max_hcl we've seen (knowledge)
    created_at     TEXT DEFAULT (datetime('now'))
);

CREATE INDEX IF NOT EXISTS idx_threads_status ON threads(status);

CREATE TABLE IF NOT EXISTS thread_observations (
    thread_id      INTEGER NOT NULL REFERENCES threads(id) ON DELETE CASCADE,
    observation_id INTEGER NOT NULL REFERENCES observations(id) ON DELETE CASCADE,
    relevance      TEXT,
    added_at       TEXT DEFAULT (datetime('now')),
    PRIMARY KEY (thread_id, observation_id)
);

CREATE TABLE IF NOT EXISTS thread_notes (
    id          INTEGER PRIMARY KEY AUTOINCREMENT,
    thread_id   INTEGER NOT NULL REFERENCES threads(id) ON DELETE CASCADE,
    note        TEXT NOT NULL,
    created_at  TEXT DEFAULT (datetime('now'))
);

-- TOPICS: TF-IDF clustered groups of related observations
CREATE TABLE IF NOT EXISTS topics (
    id          INTEGER PRIMARY KEY AUTOINCREMENT,
    name        TEXT NOT NULL,
    keywords    TEXT,
    score       REAL DEFAULT 0,
    created_at  TEXT DEFAULT (datetime('now'))
);
`