feat(provider): validate scope_filter against the v0.5 4-axis lattice
bifrost 0.7.0 (wire v0.5) makes agent_self canonical: the scope lattice is
now {end_user, group, tenant, agent_self}. Our store was MORE permissive than
bifrost's reference (no _validate_scope_filter), which silently 0-zeroed the
#295 cold recall instead of a loud 400. Now matched: search rejects an
out-of-lattice axis with InvalidFilter (-> memory.invalid_filter 400), agent_self
admitted. Purely additive — everything that validated before still validates.
Closes the parity gap our own foot-gun flag opened (bifrost-dev shipped the
lattice add #10 off it). Pin bumped bifrost>=0.6.1 -> >=0.7.0. Contract
search PRE-003 + lattice_axes test; 2 new store tests; full suite 429 green.
This commit is contained in:
@@ -209,9 +209,10 @@ FN search(self, vector: list[float], *, top_k: int, scope_filter: dict | None =
|
||||
BRIEF: Vector (cosine) recall over sqlite-vec, scoped, returning the top_k IN-SCOPE chunks.
|
||||
PRE: [PRE-001 hard] len(vector) == embedding_dim -- else InvalidArguments
|
||||
PRE: [PRE-002 hard] metadata_filter is empty/None -- v1 advertises no filterable fields; a non-empty filter → InvalidArguments
|
||||
PRE: [PRE-003 hard] every scope_filter axis ∈ {end_user, group, tenant, agent_self} -- else InvalidFilter (memory.invalid_filter 400); the bifrost wire-v0.5 lattice, matching the reference _validate_scope_filter (#10 made agent_self canonical)
|
||||
POST: [POST-001 return_value] returns the top_k highest-cosine records WHOSE scope matches scope_filter — at most top_k, and never fewer than min(top_k, in-scope count) (INV-005). Each: {chunk (verbatim), chunk_id, score, recalled_view (= chunk["distillate"] or chunk), revision} -- assert
|
||||
STEPS:
|
||||
1. [setup] validate scope_filter is a flat {axis: value} dict (matched against record["scope"][axis])
|
||||
1. [setup] validate scope_filter is a flat {axis: value} dict (matched against record["scope"][axis]) AND every axis ∈ the v0.5 lattice {end_user, group, tenant, agent_self} (else InvalidFilter)
|
||||
2. [sequential, flexibility=indicative] rank candidates by cosine over record["embedding"]; KEEP only scope-matching records (INV-005); THEN take top_k — so top_k counts IN-SCOPE hits, not pre-filter hits (over-fetch from the vec index or post-filter rank as needed)
|
||||
3. [cleanup] RETURN result rows (chunk verbatim + score + recalled_view + revision)
|
||||
TESTS:
|
||||
@@ -219,6 +220,7 @@ TESTS:
|
||||
scope_isolation [adversarial]: two scopes, search one → never returns the other's chunk, and returns top_k of the IN-SCOPE set even if out-of-scope chunks score higher (INV-005)
|
||||
empty [boundary]: search empty store → []
|
||||
metadata_filter_rejected [adversarial]: non-empty metadata_filter → InvalidArguments
|
||||
lattice_axes [adversarial]: out-of-lattice scope axis → InvalidFilter; agent_self admitted (wire v0.5, #10)
|
||||
parity_vs_reference [scenario]: identical search envelopes vs InMemoryMemoryStore → same ranked chunk_ids/shape (#195)
|
||||
```
|
||||
|
||||
|
||||
+2
-2
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
||||
|
||||
[project]
|
||||
name = "ratatoskr"
|
||||
version = "0.17.4"
|
||||
version = "0.17.5"
|
||||
description = "Worldtree Conversation API debug TUI — multi-pane observability dashboard"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.12"
|
||||
@@ -30,7 +30,7 @@ web = [
|
||||
# from the debug TUI. Recipe: bifrost/docs/implementing-a-consumer.md.
|
||||
provider = [
|
||||
"ratatoskr[web]", # reuse the starlette + uvicorn ASGI stack
|
||||
"bifrost>=0.6.1", # consumer engines + library (0.6.0 yanked: circular import)
|
||||
"bifrost>=0.7.0", # consumer engines + library (0.7.0/wire-v0.5: agent_self canonical in the scope lattice; 0.6.0 yanked: circular import)
|
||||
"jsonschema>=4", # bifrost runtime dep — envelope validation
|
||||
"sqlite-vec>=0.1.6", # vector index for the memory plane (vec0 virtual table)
|
||||
]
|
||||
|
||||
@@ -25,6 +25,7 @@ from bifrost.consumer import ConsumerRegistration, build_memory_app
|
||||
from bifrost.memory import (
|
||||
IdempotencyConflict,
|
||||
InvalidArguments,
|
||||
InvalidFilter,
|
||||
RevisionMismatch,
|
||||
StoreCapabilities,
|
||||
)
|
||||
@@ -33,6 +34,11 @@ from bifrost.reference_server import JwtVerifier
|
||||
_SHORT_RETRY_TTL_SECONDS = 300
|
||||
_DURABLE_JOB_TTL_SECONDS = 24 * 60 * 60
|
||||
|
||||
# bifrost wire v0.5 scope lattice: three subject axes + agent_self (the #248
|
||||
# agent-identity axis, made canonical in #10). An axis outside it is InvalidFilter
|
||||
# (-> memory.invalid_filter 400), matching bifrost's reference _validate_scope_filter.
|
||||
_SCOPE_LATTICE = {"end_user", "group", "tenant", "agent_self"}
|
||||
|
||||
# Inbound memory-call observability (#17 observe brick). A self-contained
|
||||
# stdout handler so the lines reliably reach the provider's stdout regardless
|
||||
# of uvicorn's logging config. INFO-level, no propagation to root.
|
||||
@@ -205,6 +211,8 @@ class RatatoskrMemoryStore:
|
||||
raise InvalidArguments("metadata_filter is unsupported in v1")
|
||||
if scope_filter is not None and not isinstance(scope_filter, dict): # STEP 1
|
||||
raise InvalidArguments("scope_filter must be a flat {axis: value} dict")
|
||||
if scope_filter and any(axis not in _SCOPE_LATTICE for axis in scope_filter):
|
||||
raise InvalidFilter("scope_filter contains unsupported axis")
|
||||
_log.info(
|
||||
"memory-call search REQUEST: scope_filter=%r top_k=%s metadata_filter=%r vec_dim=%d",
|
||||
scope_filter, top_k, metadata_filter, len(vector),
|
||||
|
||||
@@ -10,7 +10,12 @@ from __future__ import annotations
|
||||
import types
|
||||
|
||||
import pytest
|
||||
from bifrost.memory import IdempotencyConflict, InvalidArguments, RevisionMismatch
|
||||
from bifrost.memory import (
|
||||
IdempotencyConflict,
|
||||
InvalidArguments,
|
||||
InvalidFilter,
|
||||
RevisionMismatch,
|
||||
)
|
||||
|
||||
from ratatoskr.provider.memory_store import (
|
||||
build_memory_provider_app,
|
||||
@@ -221,6 +226,28 @@ async def test_search_non_dict_scope_filter_rejected():
|
||||
await store.search(_vec(1.0), top_k=5, scope_filter="u1")
|
||||
|
||||
|
||||
async def test_search_out_of_lattice_scope_axis_rejected():
|
||||
# v0.5 scope lattice = {end_user, group, tenant, agent_self}; an axis outside
|
||||
# it is InvalidFilter (-> memory.invalid_filter 400), matching bifrost's reference.
|
||||
store = open_memory_store(":memory:", embedding_dim=EMBEDDING_DIM)
|
||||
with pytest.raises(InvalidFilter):
|
||||
await store.search(_vec(1.0), top_k=5, scope_filter={"bogus_axis": "x"})
|
||||
|
||||
|
||||
async def test_search_agent_self_axis_accepted():
|
||||
# agent_self became canonical at wire v0.5 (#10) — admitted, not rejected.
|
||||
store = open_memory_store(":memory:", embedding_dim=EMBEDDING_DIM)
|
||||
await store.upsert_many(
|
||||
[_chunk("a1", scope={"agent_self": "ratatoskr:smoke"})],
|
||||
idempotency_key="k1",
|
||||
ctx=_ctx(),
|
||||
)
|
||||
results = await store.search(
|
||||
_vec(1.0), top_k=5, scope_filter={"agent_self": "ratatoskr:smoke"}
|
||||
)
|
||||
assert [r["chunk_id"] for r in results] == ["a1"]
|
||||
|
||||
|
||||
async def test_search_top_k_zero_returns_empty():
|
||||
# POST-001: at most top_k — zero means zero
|
||||
store = open_memory_store(":memory:", embedding_dim=EMBEDDING_DIM)
|
||||
|
||||
@@ -190,14 +190,14 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "bifrost"
|
||||
version = "0.6.1"
|
||||
version = "0.7.0"
|
||||
source = { registry = "https://gitea.phasefinal.com/api/packages/vh/pypi/simple/" }
|
||||
dependencies = [
|
||||
{ name = "jsonschema" },
|
||||
]
|
||||
sdist = { url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/0.6.1/bifrost-0.6.1.tar.gz", hash = "sha256:2eaf93c6da91faa6faa80a4c9a8d0c66161f4a7cc31ff041b0ae64daf3c161ea" }
|
||||
sdist = { url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/0.7.0/bifrost-0.7.0.tar.gz", hash = "sha256:27d5c2c3052ad48510a4a73973141f2177b9e1f66576ab3d8976d5c4deb5bfac" }
|
||||
wheels = [
|
||||
{ url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/0.6.1/bifrost-0.6.1-py3-none-any.whl", hash = "sha256:ed505d2c08cf4cdd0a84c68ec42f8732b4c1baf7d72befe5eacf75d88381d5ce" },
|
||||
{ url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/0.7.0/bifrost-0.7.0-py3-none-any.whl", hash = "sha256:9704c50430f350f6dde5428f79a8719e044021ce717a5eac60a13424b1ee4623" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1052,7 +1052,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "ratatoskr"
|
||||
version = "0.17.4"
|
||||
version = "0.17.5"
|
||||
source = { editable = "." }
|
||||
dependencies = [
|
||||
{ name = "httpx" },
|
||||
@@ -1086,7 +1086,7 @@ web = [
|
||||
|
||||
[package.metadata]
|
||||
requires-dist = [
|
||||
{ name = "bifrost", marker = "extra == 'provider'", specifier = ">=0.6.1", index = "https://gitea.phasefinal.com/api/packages/vh/pypi/simple/" },
|
||||
{ name = "bifrost", marker = "extra == 'provider'", specifier = ">=0.7.0", index = "https://gitea.phasefinal.com/api/packages/vh/pypi/simple/" },
|
||||
{ name = "httpx", specifier = ">=0.27" },
|
||||
{ name = "httpx-sse", specifier = ">=0.4" },
|
||||
{ name = "jsonschema", marker = "extra == 'provider'", specifier = ">=4" },
|
||||
|
||||
Reference in New Issue
Block a user