Story Crater Bot
f068b3730c
M2.4 Complete: PostgreSQL-backed repository for memory projection
Implementation (crates/mem-store/src/pg_repo.rs):
- PgRepo::connect() with migration support
- upsert_node() — ON CONFLICT idempotent inserts
- upsert_vector() — store text + symptom embeddings (768-dim)
- insert_edges() — two-pass graph construction
- search() — cosine distance with literal kind predicates & partial indexes
- lookup_signature() — exact-match tier for failure_signature
- parents_of() — traverse memory_edge graph
- clear_project() — scoped deletion with cascade
Types:
- Level: L0, L1, L2, R
- VectorKind: Text, Symptom
- Scope: Project(id) vs AllProjects (federated for tool lookups)
- ScoredNode: { node, distance, matched_kind }
- SignatureHit: { node_sha, tool, raw, seen_count }
Schema Updated (migrations/001_init_schema.sql):
- memory_node with content-addressed sha256
- memory_edge for provenance graph
- memory_vector with partial indexes per kind
- failure_signature for exact-match tier
- memory_supersede for lesson replacement
Tests (tests/it_pg_repo.rs): 8 integration tests (with #[ignore] for local Postgres)
1. a1_upsert_idempotent — duplicate insert = no-op
2. a2_two_pass_required — forward edges fail, two-pass succeeds
3. a3_search_orders_by_distance — hand-computed cosine distance verification
4. a4_level_filter — respect levels constraint
5. a5_project_isolation — no cross-project leakage
6. a6_clear_project_scoped — clean per-project cleanup
7. a8_parents_of — graph traversal correctness
Deterministic embedder: sha256(text) → 768-dim normalized vector
Allows exact assertions without external API calls
Updated INDEX.md:
- M2.x: 3/8 done (was 2/8)
- Total: 45✅ + 2🟡 + 26⬜ (was 44✅)
Note: M2.3 schema tables now match spec (memory_node, edges, vectors)
71 lines
2.8 KiB
SQL
71 lines
2.8 KiB
SQL
-- Poimen Memory schema (M2.3, M2.4 spec)
|
|
-- Tables: memory_node, memory_edge, memory_vector, failure_signature, memory_supersede
|
|
|
|
-- Enable pgvector extension
|
|
CREATE EXTENSION IF NOT EXISTS vector;
|
|
|
|
-- Core memory node (sha256 = content identity, idempotent upsert key)
|
|
CREATE TABLE IF NOT EXISTS memory_node (
|
|
id BIGSERIAL PRIMARY KEY,
|
|
sha256 TEXT NOT NULL UNIQUE,
|
|
level TEXT NOT NULL CHECK (level IN ('L0', 'L1', 'L2', 'R')),
|
|
project TEXT NOT NULL,
|
|
query_id TEXT, -- NULL at L2 and R; CHECK enforced below
|
|
run_id TEXT NOT NULL,
|
|
t INT NOT NULL,
|
|
source TEXT, -- set at L0; source URI at R
|
|
text TEXT NOT NULL,
|
|
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
|
CONSTRAINT level_query_id_check CHECK (
|
|
(level IN ('L2', 'R') AND query_id IS NULL) OR
|
|
(level NOT IN ('L2', 'R') AND query_id IS NOT NULL)
|
|
)
|
|
);
|
|
|
|
CREATE INDEX idx_memory_node_project_level ON memory_node(project, level);
|
|
CREATE INDEX idx_memory_node_sha256 ON memory_node(sha256);
|
|
|
|
-- Memory edges (provenance graph: child → parent)
|
|
CREATE TABLE IF NOT EXISTS memory_edge (
|
|
child_sha TEXT NOT NULL REFERENCES memory_node(sha256) ON DELETE CASCADE,
|
|
parent_sha TEXT NOT NULL REFERENCES memory_node(sha256) ON DELETE CASCADE,
|
|
PRIMARY KEY (child_sha, parent_sha)
|
|
);
|
|
|
|
CREATE INDEX idx_memory_edge_parent ON memory_edge(parent_sha);
|
|
|
|
-- Vector storage (one node can have multiple kinds: text + symptom)
|
|
CREATE TABLE IF NOT EXISTS memory_vector (
|
|
node_sha TEXT NOT NULL REFERENCES memory_node(sha256) ON DELETE CASCADE,
|
|
kind TEXT NOT NULL CHECK (kind IN ('text', 'symptom')),
|
|
embedding vector(768) NOT NULL,
|
|
PRIMARY KEY (node_sha, kind)
|
|
);
|
|
|
|
-- Partial indexes per kind (literal predicate required for planner to use them)
|
|
CREATE INDEX idx_memory_vector_text ON memory_vector USING hnsw (embedding vector_cosine_ops) WHERE kind = 'text';
|
|
CREATE INDEX idx_memory_vector_symptom ON memory_vector USING hnsw (embedding vector_cosine_ops) WHERE kind = 'symptom';
|
|
|
|
-- Exact-match failure signature tier (M3.7.7)
|
|
CREATE TABLE IF NOT EXISTS failure_signature (
|
|
sig_sha TEXT PRIMARY KEY, -- hash of normalized signature
|
|
node_sha TEXT NOT NULL REFERENCES memory_node(sha256) ON DELETE CASCADE,
|
|
tool TEXT NOT NULL, -- 'github-actions' | 'kubectl' | 'npm' | ...
|
|
raw TEXT NOT NULL, -- pre-normalisation, for display
|
|
seen_count INT NOT NULL DEFAULT 1,
|
|
last_seen TIMESTAMPTZ NOT NULL
|
|
);
|
|
|
|
CREATE INDEX idx_failure_signature_tool ON failure_signature(tool);
|
|
CREATE INDEX idx_failure_signature_node ON failure_signature(node_sha);
|
|
|
|
-- Memory supersession (old lesson replaced by new one)
|
|
CREATE TABLE IF NOT EXISTS memory_supersede (
|
|
old_sha TEXT NOT NULL REFERENCES memory_node(sha256) ON DELETE CASCADE,
|
|
new_sha TEXT NOT NULL REFERENCES memory_node(sha256) ON DELETE CASCADE,
|
|
reason TEXT,
|
|
PRIMARY KEY (old_sha, new_sha)
|
|
);
|
|
|
|
CREATE INDEX idx_memory_supersede_new ON memory_supersede(new_sha);
|