Files
ATOCore/tests/test_project_state.py

199 lines
6.7 KiB
Python
Raw Normal View History

"""Tests for Trusted Project State."""
import pytest
from atocore.context.project_state import (
CATEGORIES,
ensure_project,
format_project_state,
get_state,
init_project_state_schema,
invalidate_state,
set_state,
)
from atocore.models.database import init_db
@pytest.fixture(autouse=True)
def setup_db(tmp_data_dir):
"""Initialize DB and project state schema for every test."""
init_db()
init_project_state_schema()
def test_ensure_project_creates():
"""Test creating a new project."""
pid = ensure_project("test-project", "A test project")
assert pid
# Second call returns same ID
pid2 = ensure_project("test-project")
assert pid == pid2
def test_set_state_creates_entry():
"""Test creating a project state entry."""
entry = set_state("myproject", "status", "phase", "Phase 0.5 — PoC complete")
assert entry.category == "status"
assert entry.key == "phase"
assert entry.value == "Phase 0.5 — PoC complete"
assert entry.status == "active"
def test_set_state_upserts():
"""Test that setting same key updates the value."""
set_state("myproject", "status", "phase", "Phase 0")
entry = set_state("myproject", "status", "phase", "Phase 1")
assert entry.value == "Phase 1"
# Only one entry should exist
entries = get_state("myproject", category="status")
assert len(entries) == 1
assert entries[0].value == "Phase 1"
def test_set_state_invalid_category():
"""Test that invalid category raises ValueError."""
with pytest.raises(ValueError, match="Invalid category"):
set_state("myproject", "invalid_category", "key", "value")
def test_set_state_validates_confidence():
"""Project-state confidence should stay within the documented range."""
with pytest.raises(ValueError, match="Confidence must be between 0.0 and 1.0"):
set_state("myproject", "status", "phase", "Phase 1", confidence=1.2)
def test_get_state_all():
"""Test getting all state entries for a project."""
set_state("proj", "status", "phase", "Phase 1")
set_state("proj", "decision", "database", "SQLite for v1")
set_state("proj", "requirement", "latency", "<2 seconds")
entries = get_state("proj")
assert len(entries) == 3
categories = {e.category for e in entries}
assert categories == {"status", "decision", "requirement"}
def test_get_state_by_category():
"""Test filtering by category."""
set_state("proj", "status", "phase", "Phase 1")
set_state("proj", "decision", "database", "SQLite")
set_state("proj", "decision", "vectordb", "ChromaDB")
entries = get_state("proj", category="decision")
assert len(entries) == 2
assert all(e.category == "decision" for e in entries)
def test_get_state_nonexistent_project():
"""Test getting state for a project that doesn't exist."""
entries = get_state("nonexistent")
assert entries == []
def test_invalidate_state():
"""Test marking a state entry as superseded."""
set_state("invalidate-test", "decision", "approach", "monolith")
success = invalidate_state("invalidate-test", "decision", "approach")
assert success
# Active entries should be empty
entries = get_state("invalidate-test", active_only=True)
assert len(entries) == 0
# But entry still exists if we include inactive
entries = get_state("invalidate-test", active_only=False)
assert len(entries) == 1
assert entries[0].status == "superseded"
def test_invalidate_nonexistent():
"""Test invalidating a nonexistent entry."""
success = invalidate_state("proj", "decision", "nonexistent")
assert not success
def test_format_project_state():
"""Test formatting state entries for context injection."""
set_state("proj", "status", "phase", "Phase 1")
set_state("proj", "decision", "database", "SQLite", source="Build Spec V1")
entries = get_state("proj")
formatted = format_project_state(entries)
assert "--- Trusted Project State ---" in formatted
assert "--- End Project State ---" in formatted
assert "phase: Phase 1" in formatted
assert "database: SQLite" in formatted
assert "(source: Build Spec V1)" in formatted
def test_format_empty():
"""Test formatting empty state."""
assert format_project_state([]) == ""
fix(P1+P2): canonicalize project names at every trust boundary Three findings from codex's review of the previous P1+P2 fix. The earlier commit (f2372ef) only fixed alias resolution at the context builder. Codex correctly pointed out that the same fragmentation applies at every other place a project name crosses a boundary — project_state writes/reads, interaction capture/listing/filtering, memory create/queries, and reinforcement's downstream queries. Plus a real bug in the interaction `since` filter where the storage format and the documented ISO format don't compare cleanly. The fix is one helper used at every boundary instead of duplicating the resolution inline. New helper: src/atocore/projects/registry.py::resolve_project_name --------------------------------------------------------------- - Single canonicalization boundary for project names - Returns the canonical project_id when the input matches any registered id or alias - Returns the input unchanged for empty/None and for unregistered names (preserves backwards compat with hand-curated state that predates the registry) - Documented as the contract that every read/write at the trust boundary should pass through P1 — Trusted Project State endpoints ------------------------------------ src/atocore/context/project_state.py: set_state, get_state, and invalidate_state now all canonicalize project_name through resolve_project_name BEFORE looking up or creating the project row. Before this fix: - POST /project/state with project="p05" called ensure_project("p05") which created a separate row in the projects table - The state row was attached to that alias project_id - Later context builds canonicalized "p05" -> "p05-interferometer" via the builder fix from f2372ef and never found the state - Result: trusted state silently fragmented across alias rows After this fix: - The alias is resolved to the canonical id at every entry point - Two captures (one via "p05", one via "p05-interferometer") write to the same row - get_state via either alias or the canonical id finds the same row Fixes the highest-priority gap codex flagged because Trusted Project State is supposed to be the most dependable layer in the AtoCore trust hierarchy. P2.a — Interaction capture project canonicalization ---------------------------------------------------- src/atocore/interactions/service.py: record_interaction now canonicalizes project before storing, so interaction.project is always the canonical id regardless of what the client passed. Downstream effects: - reinforce_from_interaction queries memories by interaction.project -> previously missed memories stored under canonical id -> now consistent because interaction.project IS the canonical id - the extractor stamps candidates with interaction.project -> previously created candidates in alias buckets -> now creates candidates in the canonical bucket - list_interactions(project=alias) was already broken, now fixed by canonicalizing the filter input on the read side too Memory service applied the same fix: - src/atocore/memory/service.py: create_memory and get_memories both canonicalize project through resolve_project_name - This keeps stored memory.project consistent with the reinforcement query path P2.b — Interaction `since` filter format normalization ------------------------------------------------------ src/atocore/interactions/service.py: new _normalize_since helper. The bug: - created_at is stored as 'YYYY-MM-DD HH:MM:SS' (no timezone, UTC by convention) so it sorts lexically and compares cleanly with the SQLite CURRENT_TIMESTAMP default - The `since` parameter was documented as ISO 8601 but compared as a raw string against the storage format - The lexically-greater 'T' separator means an ISO timestamp like '2026-04-07T12:00:00Z' is GREATER than the storage form '2026-04-07 12:00:00' for the same instant - Result: a client passing ISO `since` got an empty result for any row from the same day, even though those rows existed and were technically "after" the cutoff in real-world time The fix: - _normalize_since accepts ISO 8601 with T, optional Z suffix, optional fractional seconds, optional +HH:MM offsets - Uses datetime.fromisoformat for parsing (Python 3.11+) - Converts to UTC and reformats as the storage format before the SQL comparison - The bare storage format still works (backwards compat path is a regex match that returns the input unchanged) - Unparseable input is returned as-is so the comparison degrades gracefully (rows just don't match) instead of raising and breaking the listing endpoint builder.py refactor ------------------- The previous P1 fix had inline canonicalization. Now it uses the shared helper for consistency: - import changed from get_registered_project to resolve_project_name - the inline lookup is replaced with a single helper call - the comment block now points at representation-authority.md for the canonicalization contract New shared test fixture: tests/conftest.py::project_registry ------------------------------------------------------------ - Standardizes the registry-setup pattern that was duplicated across test_context_builder.py, test_project_state.py, test_interactions.py, and test_reinforcement.py - Returns a callable that takes (project_id, [aliases]) tuples and writes them into a temp registry file with the env var pointed at it and config.settings reloaded - Used by all 12 new regression tests in this commit Tests (12 new, all green on first run) -------------------------------------- test_project_state.py: - test_set_state_canonicalizes_alias: write via alias, read via every alias and the canonical id, verify same row id - test_get_state_canonicalizes_alias_after_canonical_write - test_invalidate_state_canonicalizes_alias - test_unregistered_project_state_still_works (backwards compat) test_interactions.py: - test_record_interaction_canonicalizes_project - test_list_interactions_canonicalizes_project_filter - test_list_interactions_since_accepts_iso_with_t_separator - test_list_interactions_since_accepts_z_suffix - test_list_interactions_since_accepts_offset - test_list_interactions_since_storage_format_still_works test_reinforcement.py: - test_reinforcement_works_when_capture_uses_alias (end-to-end: capture under alias, seed memory under canonical, verify reinforcement matches) - test_get_memories_filter_by_alias Full suite: 174 passing (was 162), 1 warning. The +12 is the new regression tests, no existing tests regressed. What's still NOT canonicalized (and why) ---------------------------------------- - _rank_chunks's secondary substring boost in builder.py — the retriever already does the right thing via its own _project_match_boost which calls get_registered_project. The redundant secondary boost still uses the raw hint but it's a multiplicative factor on top of correct retrieval, not a filter, so it can't drop relevant chunks. Tracked as a future cleanup but not a P1. - update_memory's project field (you can't change a memory's project after creation in the API anyway). - The retriever's project_hint parameter on direct /query calls — same reasoning as the builder boost, plus the retriever's own get_registered_project call already handles aliases there.
2026-04-07 08:29:33 -04:00
# --- Alias canonicalization regression tests --------------------------------
def test_set_state_canonicalizes_alias(project_registry):
"""Writing state via an alias should land under the canonical project id.
Regression for codex's P1 finding: previously /project/state with
project="p05" created a separate alias row that later context builds
(which canonicalize the hint) would never see.
"""
project_registry(("p05-interferometer", ["p05", "interferometer"]))
set_state("p05", "status", "next_focus", "Wave 2 ingestion")
# The state must be reachable via every alias AND the canonical id
via_alias = get_state("p05")
via_canonical = get_state("p05-interferometer")
via_other_alias = get_state("interferometer")
assert len(via_alias) == 1
assert len(via_canonical) == 1
assert len(via_other_alias) == 1
# All three reads return the same row id (no fragmented duplicates)
assert via_alias[0].id == via_canonical[0].id == via_other_alias[0].id
assert via_canonical[0].value == "Wave 2 ingestion"
def test_get_state_canonicalizes_alias_after_canonical_write(project_registry):
"""Reading via an alias should find state written under the canonical id."""
project_registry(("p04-gigabit", ["p04", "gigabit"]))
set_state("p04-gigabit", "status", "phase", "Phase 1 baseline")
via_alias = get_state("gigabit")
assert len(via_alias) == 1
assert via_alias[0].value == "Phase 1 baseline"
def test_invalidate_state_canonicalizes_alias(project_registry):
"""Invalidating via an alias should hit the canonical row."""
project_registry(("p06-polisher", ["p06", "polisher"]))
set_state("p06-polisher", "decision", "frame", "kinematic mounts")
success = invalidate_state("polisher", "decision", "frame")
assert success is True
active = get_state("p06-polisher")
assert len(active) == 0
def test_unregistered_project_state_still_works(project_registry):
"""Hand-curated state for an unregistered project must still round-trip.
Backwards compatibility with state created before the project
registry existed: resolve_project_name returns the input unchanged
when the registry has no record, so the raw name is used as-is.
"""
project_registry() # empty registry
set_state("orphan-project", "status", "phase", "Standalone")
entries = get_state("orphan-project")
assert len(entries) == 1
assert entries[0].value == "Standalone"