Nick
ca4f7593d7
CI Pipeline / best-practices (push) Successful in 8s
Auto-version and Release / release (push) Failing after 14s
CI Pipeline / documentation (push) Successful in 5s
CI Pipeline / lint (push) Failing after 34s
CI Pipeline / canary (push) Successful in 37s
CI Pipeline / type-check (push) Successful in 31s
CI Pipeline / gitea-offline (push) Successful in 16s
CI Pipeline / unit-tests (push) Successful in 1m4s
CI Pipeline / required-checks (push) Successful in 1s
deploy / deploy (push) Successful in 48s
CORRECTION 1: #314 reopened — recall_with_associations mode field defect CONFIRMED in current source and FIXED (mode: association_merged). CORRECTION 3: Gitea credential removed from remote URL (credential helper). TOKEN EXPOSED: yes (in diagnostic output). TOKEN ROTATED: not yet (requires Gitea web UI access). Remote URL now shows username only, no secret. CORRECTION 4: duplicate-release-commit defect ROOT CAUSE: convergence computed warranted bump from commits-since-tag without checking if master version already satisfies the bump. FIX: already-converged guard in version_convergence.py (master version > last tag → no commit). Repo-aware (args.repo passed to read_version/latest_tag). CORRECTION 6: lifecycle terminalization — execution exception now guarantees task terminalizes as failed with evidence (no immortal RUNNING). CORRECTION 7: route instruction task-scoped on RuneTask.route_instruction (NOT shared operator state). Read-only leading-verb override. Isolation tests prove no cross-contamination between interleaved tasks. PL1-01/02/03/05: pl1_records.py (route resolution, proof level, failure class, candidate status), metrics with honest NOT_YET_MEASURABLE semantics, route-instruction learning loop (PE-1789102658-0269 SEED). 1253 tests green; ratchet 352/80 (shrink); henxels clean.
77 lines
3.0 KiB
Python
77 lines
3.0 KiB
Python
"""Tests: ISSUE deterministic intake/gate (replaces cognitive DEFINE).
|
|
|
|
The Gitea issue is the authoritative statement of intent. This gate only
|
|
compiles the contract — no model invocation, ever. Ambiguity is recorded
|
|
as a signal, not a MiMo trigger.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import importlib.util
|
|
from pathlib import Path
|
|
|
|
ROOT = Path(__file__).resolve().parent.parent
|
|
SPEC = importlib.util.spec_from_file_location("research_define", ROOT / "scripts" / "research_define.py")
|
|
rd = importlib.util.module_from_spec(SPEC)
|
|
SPEC.loader.exec_module(rd)
|
|
|
|
|
|
def test_bug_issue_is_repo_specific():
|
|
issue = {
|
|
"number": 1,
|
|
"title": "Fix memory leak in shard_manager",
|
|
"body": "The shard manager leaks connections when topics are created rapidly.",
|
|
}
|
|
c = rd.compile_define_contract(issue)
|
|
assert c["question_type"] == "repo-specific"
|
|
assert c["needs_mimo"] is False # ISSUE NEVER invokes a model
|
|
assert "OUTWARD" not in c["required_stages"]
|
|
|
|
|
|
def test_architecture_issue_is_mixed():
|
|
issue = {
|
|
"number": 2,
|
|
"title": "Design the memory selection architecture",
|
|
"body": "We need to choose the best approach for hybrid recall. Compare alternatives and benchmark them.",
|
|
}
|
|
c = rd.compile_define_contract(issue)
|
|
assert c["question_type"] in ("mixed", "current-tech")
|
|
assert "OUTWARD" in c["required_stages"]
|
|
# Design indicators → INNOVATION_WARRANTED is credible, so INNOVATION included
|
|
assert "INNOVATION" in c["required_stages"]
|
|
|
|
|
|
def test_simple_bug_skips_outward():
|
|
issue = {"number": 3, "title": "Fix import error in tui_validator", "body": "The import allowlist is wrong."}
|
|
c = rd.compile_define_contract(issue)
|
|
assert "OUTWARD" in c.get("skipped_stages", {})
|
|
assert "INWARD" in c["required_stages"]
|
|
|
|
|
|
def test_subquestions_extracted():
|
|
issue = {
|
|
"number": 4,
|
|
"title": "Evaluate memory backends",
|
|
"body": "Which backend is fastest?\nWhat about memory usage?\nDoes it support concurrent access?",
|
|
}
|
|
c = rd.compile_define_contract(issue)
|
|
assert len(c["sub_questions"]) >= 2
|
|
|
|
|
|
def test_ambiguous_issue_records_signal_not_mimo():
|
|
"""Ambiguity is a recorded signal for downstream stages — NOT a model trigger.
|
|
ISSUE must never invoke MiMo, even when the issue is ambiguous."""
|
|
issue = {"number": 5, "title": "?", "body": ""}
|
|
c = rd.compile_define_contract(issue)
|
|
assert c["ambiguous"] is True
|
|
assert c["needs_mimo"] is False
|
|
|
|
|
|
def test_retired_stage_names_absent_from_contract():
|
|
"""Retired stages must not appear in any compiled contract field."""
|
|
for body in ("fix bug", "design architecture approach", "compare and benchmark"):
|
|
c = rd.compile_define_contract({"number": 9, "title": "t", "body": body})
|
|
for field in ("required_stages", "skipped_stages"):
|
|
for retired in ("DEFINE", "OUTWARD_DISCOVERY", "OUTWARD_READING"):
|
|
assert retired not in c[field], f"{retired} leaked into {field}"
|