Files
roboco/tests/unit/api/test_schemas_v1_flow.py
T
e9ca7d4036 Delegation detail-fidelity + PM-loop hardening (#541)
* feat(gateway): delegation detail-fidelity — details survive hand-off, both directions

Details thinned out at every delegation hop: a PM child task mapped to no
parent criterion was legal (coverage only surfaced at submit_up, after the
whole wave ran — a 12-subtask docs tree grew through 8 review rounds that
way, one child titled 'docs page and route wrapper' shipping only the
page), and QA could pass work on a gestalt read (a 4-scene video brief
shipped 3 scenes past every gate because the features existed only in
prose). Three chokepoint gates:

- delegate (down): every child must declare covers_parent_criteria
  resolving against the parent's real acceptance criteria — no mapping or
  an unresolvable ref rejects naming every offending child and the valid
  criteria; the success envelope carries parent_ac_coverage
  {covered, uncovered} so a wave-planning PM sees remaining gaps in the
  same turn. Full coverage stays enforced at submit_up (waves stay legal).
- pass_review (up): mandatory criteria_verified — one {criterion,
  evidence} entry per task AC, matched by the findings ledger's
  id-or-exact-text matcher, evidence soup-checked and capped; rejects
  naming the unverified criteria; entries render deterministically into
  qa_notes as '[AC] <criterion> — verified: <evidence>' lines. The old
  count-only ac_verdicts gate is superseded (arg kept for back-compat).
- video briefs (structured detail at origination): an enumerable feature
  list (release highlights, or input_props.highlights carried onto a
  reject re-author) becomes its own scene acceptance criterion, bounded to
  the AC caps; a re-author without highlights carries the
  feedback-addressed criterion instead.

Extracted findings.py's criterion matcher into shared unmatched_criteria /
uncovered_acceptance_criteria instead of duplicating it; criteria_verified
joins the WAF free-text exclusion set like findings/issues.

* fix(gateway): break the block/unblock wedge — four hardening fixes from the live PM loop

A cell task looped fe-pm/main-pm block/unblock for hours (10 cycles, 43
spawns): a transient GitHub API error resolving CI became an unwaivable
blocker finding whose own fix text said no code change was required, the
submit freshness guard then demanded a commit no finding called for,
escalate_up auto-blocked, and main-pm's correct recovery plan 422'd on
the approach length cap, degrading it to a bare unblock. Four fixes:

- pr_pass CI-unresolvable refusal is now explicitly transient-worded:
  retry pr_pass shortly, do NOT pr_fail over a CI-status lookup error —
  a platform blip is not a code finding
- submit freshness guard grants ONE unchanged-head resubmission per
  head sha when the findings ledger has zero open rows (all addressed
  without code changes) — stamped via the resubmit_unchanged_head
  marker so the same head can never loop a second time
- unblock carries a flip breaker: block_flip_count marker, and at the
  third flip a one-shot CEO notification flags the task as structurally
  wedged (unblock itself still succeeds — the breaker signals, it does
  not wedge recovery)
- i_will_plan's approach cap truncates at 800 chars instead of
  rejecting — an over-detailed plan must never cost the PM its turn

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-17 01:52:33 +02:00

271 lines
10 KiB
Python

"""Schema-level tests for v1 flow request bodies."""
from __future__ import annotations
from typing import Any
from uuid import uuid4
import pytest
from pydantic import ValidationError
from roboco.api.schemas.v1.flow import (
_APPROACH_MAX_CHARS,
DelegateRequest,
IWillPlanRequest,
IWillWorkOnRequest,
SubTaskCreate,
)
from roboco.models.base import Complexity
def test_delegate_request_requires_task_type() -> None:
"""task_type must be supplied explicitly — no magic default.
Background: the 2026-05-08 smoke-test trace showed main-pm calling
delegate without task_type, the schema defaulted to 'code', the
cell PM downstream couldn't plan a code-typed parent (pre-fix), and
the run deadlocked. Make the field required so misuse fails at the
HTTP boundary with a clear 422.
"""
with pytest.raises(ValidationError) as exc:
DelegateRequest.model_validate(
{
"parent_task_id": uuid4(),
"title": "t",
"description": "add the new endpoint plus tests",
"assigned_to": "be-dev-1",
"team": "backend",
"nature": "technical",
"estimated_complexity": "medium",
"acceptance_criteria": ["returns 200"],
# task_type intentionally omitted
}
)
assert "task_type" in str(exc.value)
def test_delegate_request_accepts_explicit_task_type() -> None:
req = DelegateRequest(
parent_task_id=uuid4(),
title="t",
description="add the new endpoint plus tests",
assigned_to="be-dev-1",
team="backend",
task_type="code",
nature="technical",
estimated_complexity=Complexity.MEDIUM,
acceptance_criteria=["returns 200"],
)
assert req.task_type == "code"
# ---------------------------------------------------------------------------
# StrList — SDK-nested list-of-strings coercion (Bug A)
# ---------------------------------------------------------------------------
def test_i_will_plan_request_flattens_sdk_nested_technical_considerations() -> None:
"""The Claude SDK parses XML-ish ``<item>…</item>`` list-of-strings tool
input into nested arrays (``[[["…"]]]``). A bare ``list[str]`` field
hard-rejects element 1 (a list, not a str) at validation time — the live
``i_will_plan`` crash: ``technical_considerations.1 Input should be a
valid string``. The ``StrList`` BeforeValidator must flatten it to a flat
``list[str]`` so the verb body receives clean strings.
"""
# The SDK nests list-of-strings tool input as nested arrays / dict-wrapped
# text (``[[["…"]]]``, ``{"item": {"$text": "…"}}``). Annotated ``list[Any]``
# so mypy accepts the coerce-able shape; the ``StrList`` BeforeValidator
# flattens it to ``list[str]`` at runtime (no ``type: ignore`` owed).
technical_considerations: list[Any] = [
[[["Empty state distinct from loaded state, coverage target 80%"]]],
[{"item": {"$text": "Use asyncpg prepared statements"}}],
]
req = IWillPlanRequest(
task_id=uuid4(),
plan="Plan narrative describing the approach in full sentences.",
approach=(
"Approach text long enough to clear the 150-character minimum "
"enforced on the plan's Approach field so the Plan tab is fully "
"populated for audit and tracing instead of rendering an empty view."
),
technical_considerations=technical_considerations,
)
assert req.technical_considerations == [
"Empty state distinct from loaded state, coverage target 80%",
"Use asyncpg prepared statements",
]
def test_i_will_work_on_request_flattens_dict_wrapped_technical_considerations() -> (
None
):
"""Same coercion on the developer planning verb — a dict-wrapped string
(``{"item": {"$text": "…"}}``, the SDK's element-text marker) must reduce
to the bare string, not ``str(dict)``."""
technical_considerations: list[Any] = [
{"item": {"$text": "Cache the lookup result"}}
]
req = IWillWorkOnRequest(
task_id=uuid4(),
technical_considerations=technical_considerations,
)
assert req.technical_considerations == ["Cache the lookup result"]
def test_delegate_request_flattens_sdk_nested_acceptance_criteria() -> None:
"""``delegate``'s ``acceptance_criteria`` is the same list-of-strings shape
the SDK can nest (this is the ``delegate``-verb analogue of the MegaTask
Bug 3 crash). The ``StrList`` field must flatten the nested input so the
VARCHAR[] insert downstream never sees a dict/list element."""
acceptance_criteria: list[Any] = [
[[["returns 200 for valid input"]]],
[{"item": {"$text": "rejects malformed input with 400"}}],
]
req = DelegateRequest(
parent_task_id=uuid4(),
title="t",
description="add the new endpoint plus tests",
assigned_to="be-dev-1",
team="backend",
task_type="code",
nature="technical",
estimated_complexity=Complexity.MEDIUM,
acceptance_criteria=acceptance_criteria,
)
assert req.acceptance_criteria == [
"returns 200 for valid input",
"rejects malformed input with 400",
]
def test_strlist_drops_non_string_junk_instead_of_crashing() -> None:
"""Non-string junk (a bare int, a dict with no string values, whitespace)
is dropped — the field never raises on garbage the SDK might emit; only
real strings survive. An all-junk payload yields an empty list (the
delegate min_length=1 gate then rejects it cleanly, not a 500)."""
technical_considerations: list[Any] = [42, {"foo": 123}, [[" "]], "real note"]
req = IWillWorkOnRequest(
task_id=uuid4(),
technical_considerations=technical_considerations,
)
assert req.technical_considerations == ["real note"]
# ---------------------------------------------------------------------------
# Task-content guardrails (2026-07-07): ceilings on plan content + AC caps.
# ---------------------------------------------------------------------------
def test_i_will_plan_request_rejects_overlong_plan() -> None:
"""plan >2000 chars is rejected at the boundary — the bloat defect."""
with pytest.raises(ValidationError) as exc:
IWillPlanRequest(
task_id=uuid4(),
plan="x" * 2001,
approach="a" * 150,
)
assert "plan" in str(exc.value)
def test_i_will_plan_request_truncates_overlong_approach() -> None:
"""approach >800 chars is truncated to 800 (797 + "..."), never rejected —
a hard 422 here used to throw away an otherwise-good plan and degrade the
PM to a bare unblock (live incident)."""
req = IWillPlanRequest(
task_id=uuid4(),
plan="plan",
approach="a" * (_APPROACH_MAX_CHARS + 1),
)
assert len(req.approach) == _APPROACH_MAX_CHARS
assert req.approach.endswith("...")
assert req.approach == "a" * (_APPROACH_MAX_CHARS - 3) + "..."
def test_i_will_plan_request_approach_exactly_800_untruncated() -> None:
"""Exactly the ceiling is the boundary — passes through byte-for-byte."""
approach = "a" * _APPROACH_MAX_CHARS
req = IWillPlanRequest(task_id=uuid4(), plan="plan", approach=approach)
assert req.approach == approach
assert not req.approach.endswith("...")
def test_i_will_plan_request_rejects_thin_approach() -> None:
"""approach <150 chars is still a hard reject — a thin plan IS a defect."""
with pytest.raises(ValidationError) as exc:
IWillPlanRequest(
task_id=uuid4(),
plan="plan",
approach="a" * 149,
)
assert "approach" in str(exc.value)
def test_i_will_plan_request_rejects_overlong_subtask_title() -> None:
with pytest.raises(ValidationError):
IWillPlanRequest(
task_id=uuid4(),
plan="plan",
approach="a" * 150,
sub_tasks=[SubTaskCreate(title="t" * 201, description="d" * 30)],
)
def test_i_will_plan_request_rejects_overlong_subtask_description() -> None:
with pytest.raises(ValidationError):
IWillPlanRequest(
task_id=uuid4(),
plan="plan",
approach="a" * 150,
sub_tasks=[SubTaskCreate(title="ok title", description="d" * 601)],
)
def test_i_will_plan_request_rejects_thin_subtask_description() -> None:
"""A sub_task description <20 chars fails the typed SubTaskCreate model."""
with pytest.raises(ValidationError):
IWillPlanRequest(
task_id=uuid4(),
plan="plan",
approach="a" * 150,
sub_tasks=[SubTaskCreate(title="ok title", description="too short")],
)
def test_delegate_request_rejects_overlong_acceptance_criterion() -> None:
"""An AC item >200 chars is rejected — a criterion that long is a restated
description, not a verifiable outcome."""
long_ac = "x" * 201
with pytest.raises(ValidationError) as exc:
DelegateRequest.model_validate(
{
"parent_task_id": uuid4(),
"title": "t",
"description": "add the new endpoint plus tests",
"assigned_to": "be-dev-1",
"team": "backend",
"task_type": "code",
"nature": "technical",
"estimated_complexity": "medium",
"acceptance_criteria": [long_ac],
}
)
assert "acceptance_criteria" in str(exc.value)
def test_delegate_request_rejects_too_many_acceptance_criteria() -> None:
"""An AC list >7 items is rejected — over-decomposition of criteria."""
with pytest.raises(ValidationError) as exc:
DelegateRequest.model_validate(
{
"parent_task_id": uuid4(),
"title": "t",
"description": "add the new endpoint plus tests",
"assigned_to": "be-dev-1",
"team": "backend",
"task_type": "code",
"nature": "technical",
"estimated_complexity": "medium",
"acceptance_criteria": [f"criterion {i}" for i in range(8)],
}
)
assert "acceptance_criteria" in str(exc.value)