-- Phase 0 — Workstream A2: foundation schema for the agentic system.
--
-- ADDITIVE AND REVERSIBLE ONLY (CLAUDE.md guardrail #3): this migration adds
-- new tables and new nullable columns alongside the existing CRM. It never
-- drops, renames, or rewrites existing data. Its reversal is 0001_phase0_foundation.down.sql.
--
-- Applied once at startup by backend/core_migrations.py, tracked in the
-- schema_migrations ledger. Safe to leave in place; the canonical layer it
-- creates starts EMPTY and is populated later by entity resolution (A4/B3).

-- ============================================================================
-- 1. canonical_entities — the single, model-agnostic identity for an LP /
--    organization / person. Both the classic contacts/lp_profiles model and the
--    fundraising_* grid map INTO this; neither existing model is demoted.
--    IDs are full-length (e.g. 'lp_' + uuid4 hex), NOT the 8-char truncated
--    UUIDs used elsewhere in the CRM, so they are safe as the index/payload key.
-- ============================================================================
CREATE TABLE IF NOT EXISTS canonical_entities (
    id                    TEXT PRIMARY KEY,
    entity_kind           TEXT NOT NULL,            -- 'lp' | 'organization' | 'person'
    display_name          TEXT NOT NULL,
    primary_email         TEXT,
    -- Phase-0 LP/prospect fields (model-agnostic home):
    thesis_fit            TEXT,
    segment               TEXT,
    accreditation_status  TEXT,                     -- free-text until counsel defines the vocabulary (guardrail #6)
    qp_status             TEXT,
    warmth_score          REAL,
    source                TEXT,
    owner_id              TEXT REFERENCES users(id),
    last_touch_at         TEXT,
    notes                 TEXT,
    created_at            TEXT DEFAULT (datetime('now')),
    updated_at            TEXT DEFAULT (datetime('now')),
    deleted_at            TEXT                       -- soft-delete (never hard-delete; guardrail #3)
);
CREATE INDEX IF NOT EXISTS idx_canonical_kind  ON canonical_entities(entity_kind);
CREATE INDEX IF NOT EXISTS idx_canonical_email ON canonical_entities(primary_email);
CREATE INDEX IF NOT EXISTS idx_canonical_owner ON canonical_entities(owner_id);

-- ============================================================================
-- 2. entity_links — resolution map. Every source row (a contacts row, a
--    fundraising_investors row, etc.) and every email/name variant points at the
--    canonical entity it resolves to. This is how name variants collapse to one id.
-- ============================================================================
CREATE TABLE IF NOT EXISTS entity_links (
    id            TEXT PRIMARY KEY,
    canonical_id  TEXT NOT NULL REFERENCES canonical_entities(id) ON DELETE CASCADE,
    source_model  TEXT NOT NULL,    -- contacts|organizations|lp_profiles|fundraising_investors|fundraising_contacts|email_address|alias
    source_id     TEXT,             -- the local PK in that model (NULL for a bare email/name alias)
    match_value   TEXT,             -- normalized email or name variant
    match_kind    TEXT NOT NULL,    -- exact_email|name_variant|domain|manual
    confidence    REAL DEFAULT 1.0,
    created_at    TEXT DEFAULT (datetime('now')),
    UNIQUE(source_model, source_id, match_value)
);
CREATE INDEX IF NOT EXISTS idx_entity_links_canonical ON entity_links(canonical_id);
CREATE INDEX IF NOT EXISTS idx_entity_links_match     ON entity_links(match_value);
CREATE INDEX IF NOT EXISTS idx_entity_links_source    ON entity_links(source_model, source_id);

-- ============================================================================
-- 3. interaction_log — APPEND-ONLY record of every agent action and every human
--    touch (guardrail #5). Distinct from audit_log (which is mutation-diff-only
--    and has no actor/agent dimension). Nothing in this table is ever updated or
--    deleted by convention.
-- ============================================================================
CREATE TABLE IF NOT EXISTS interaction_log (
    id           TEXT PRIMARY KEY,
    ts           TEXT NOT NULL DEFAULT (datetime('now')),  -- event time
    actor_type   TEXT NOT NULL,    -- human | agent | system
    actor_id     TEXT,             -- users.id, or an agent name (Scout/Analyst/...)
    action       TEXT NOT NULL,    -- e.g. note.created | email.matched | enrichment.written | search.run
    target_type  TEXT,             -- canonical_entity | contact | communication | opportunity | ...
    target_id    TEXT,             -- canonical_entities.id where possible
    payload      TEXT,             -- JSON blob with the action detail
    source       TEXT,             -- crm_ui | mcp | ingest | scout | ...
    created_at   TEXT DEFAULT (datetime('now'))
);
CREATE INDEX IF NOT EXISTS idx_interaction_target ON interaction_log(target_type, target_id);
CREATE INDEX IF NOT EXISTS idx_interaction_ts     ON interaction_log(ts);
CREATE INDEX IF NOT EXISTS idx_interaction_actor  ON interaction_log(actor_type, actor_id);

-- ============================================================================
-- 4. relationship_edges — derived graph of who-knows-whom between canonical
--    entities. Starts EMPTY; seeded later from email_investor_links + calendar +
--    X follower overlap (Analyst, Phase 2).
-- ============================================================================
CREATE TABLE IF NOT EXISTS relationship_edges (
    id            TEXT PRIMARY KEY,
    src_id        TEXT NOT NULL REFERENCES canonical_entities(id) ON DELETE CASCADE,
    dst_id        TEXT NOT NULL REFERENCES canonical_entities(id) ON DELETE CASCADE,
    edge_type     TEXT NOT NULL,    -- email_corr | calendar | x_follow | intro | colleague
    source        TEXT NOT NULL,    -- provenance of this edge
    strength      REAL DEFAULT 0,
    directed      INTEGER DEFAULT 0,
    evidence      TEXT,             -- JSON supporting detail
    first_seen_at TEXT,
    last_seen_at  TEXT,
    created_at    TEXT DEFAULT (datetime('now')),
    updated_at    TEXT DEFAULT (datetime('now')),
    UNIQUE(src_id, dst_id, edge_type, source)
);
CREATE INDEX IF NOT EXISTS idx_rel_src ON relationship_edges(src_id);
CREATE INDEX IF NOT EXISTS idx_rel_dst ON relationship_edges(dst_id);

-- ============================================================================
-- 5. Soft-delete columns on existing tables. Additive nullable columns; the CRM
--    currently HARD-deletes everywhere (guardrail #3 gap). Adding the column is
--    safe now; switching the DELETE handlers to set it instead of hard-deleting
--    is a separate, reviewed code change.
-- ============================================================================
ALTER TABLE contacts       ADD COLUMN deleted_at TEXT;
ALTER TABLE organizations  ADD COLUMN deleted_at TEXT;
ALTER TABLE opportunities  ADD COLUMN deleted_at TEXT;
ALTER TABLE communications ADD COLUMN deleted_at TEXT;
ALTER TABLE lp_profiles    ADD COLUMN deleted_at TEXT;