cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.0k Pull Requests 115 Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into tdd/m4-plan-correct-auto-resolve
CI / benchmark-publish (pull_request) Has been skipped
Details
CI / build (pull_request) Successful in 16s
Details
CI / helm (pull_request) Successful in 23s
Details
CI / typecheck (pull_request) Successful in 1m10s
Details
CI / security (pull_request) Successful in 1m11s
Details
CI / lint (pull_request) Successful in 3m20s
Details
CI / quality (pull_request) Successful in 3m42s
Details
CI / unit_tests (pull_request) Successful in 9m9s
Details
CI / docker (pull_request) Successful in 1m18s
Details
CI / coverage (pull_request) Successful in 12m27s
Details
CI / e2e_tests (pull_request) Successful in 19m59s
Details
CI / integration_tests (pull_request) Successful in 25m8s
Details
CI / status-check (pull_request) Successful in 2s
Details
CI / benchmark-regression (pull_request) Successful in 55m21s
Details

Browse Source
This commit is contained in:
Brent Edwards
2026-04-01 00:00:48 +00:00
committed by Forgejo
parent 444f07a37c 01b6eb1804
commit 0f3191ea06
20 changed files with 201 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmarks/subplan_execution_bench.py
+15
View File
@@ -48,10 +48,17 @@ class SubplanExecutionSchedulerSuite:
def setup(self) -> None:
"""Prepare fixtures for scheduler benchmarks."""
self.statuses = [_make_status(_S1), _make_status(_S2), _make_status(_S3)]
self.statuses_15 = [
_make_status(f"01HGZ6FE0AQDYTR4BXVQ{i:06d}") for i in range(15)
]
self.seq_config = SubplanConfig(execution_mode=ExecutionMode.SEQUENTIAL)
self.par_config = SubplanConfig(
execution_mode=ExecutionMode.PARALLEL, max_parallel=3
)
self.par_scale_config = SubplanConfig(
execution_mode=ExecutionMode.PARALLEL,
max_parallel=10,
)
self.dep_config = SubplanConfig(execution_mode=ExecutionMode.DEPENDENCY_ORDERED)
self.dep_graph = {_S1: [], _S2: [_S1], _S3: [_S2]}
@@ -69,6 +76,14 @@ class SubplanExecutionSchedulerSuite:
)
service.execute_all(subplan_statuses=self.statuses, base_files={})
def time_parallel_execution_15_subplans(self) -> None:
"""Time parallel execution of 15 subplans with max_parallel=10."""
service = SubplanExecutionService(
config=self.par_scale_config,
executor_fn=_noop_executor,
)
service.execute_all(subplan_statuses=self.statuses_15, base_files={})
def time_dependency_ordered_execution(self) -> None:
"""Time dependency-ordered execution of 3 subplans."""
service = SubplanExecutionService(
features/large_project_decomposition.feature
+17
View File
@@ -19,6 +19,23 @@ Feature: Large-project hierarchical decomposition
When I decompose with max_depth 2
Then the decomposition result should have max_depth_reached <= 2
# NOTE: The test fixture ``make_files`` places all files under a single
# tmpdir root, so ``_directory_key(depth=2)`` yields one bucket and
# meaningful multi-level splits depend on bucket-size chunking.
# In production, real directory trees with distinct top-level
# subtrees will decompose to 4+ levels. A separate Robot E2E suite
# (m6_e2e_verification.robot) validates the full 4+ level requirement
# against a realistic project layout.
Scenario: Decomposition produces meaningful hierarchy for large file sets
Given a project with 5000 files across 8 directory levels
When I decompose with max_depth 4
Then the decomposition result should have max_depth_reached >= 1
Scenario: Small project decomposition depth does not increase unexpectedly
Given a project with 40 files across 3 directory levels
When I decompose with max_depth 4
Then the decomposition result should have max_depth_reached <= 2
# --- bounded context ---------------------------------------------------
Scenario: Leaf nodes respect max_files_per_subplan
features/steps/subplan_execution_steps.py
+34 -5
View File
@@ -32,6 +32,23 @@ _S2 = "01HGZ6FE0AQDYTR4BXVQZ6EB00"
_S3 = "01HGZ6FE0AQDYTR4BXVQZ6EC00"
_S4 = "01HGZ6FE0AQDYTR4BXVQZ6ED00"
_S5 = "01HGZ6FE0AQDYTR4BXVQZ6EE00"
_SEEDED_IDS = (_S1, _S2, _S3, _S4, _S5)
def _ids_for_count(n: int) -> list[str]:
"""Return *n* deterministic ULID-like identifiers.
Preserves legacy fixed IDs for the first five subplans so existing
step assertions that reference ``_S1``/``_S2``/``_S3`` continue to work,
and deterministically generates additional IDs for scale scenarios.
"""
if n <= len(_SEEDED_IDS):
return list(_SEEDED_IDS[:n])
generated = list(_SEEDED_IDS)
for idx in range(len(_SEEDED_IDS), n):
generated.append(f"01HGZ6FE0AQDYTR4BXVQ{idx:06d}")
return generated
def _make_status(
@@ -80,7 +97,7 @@ def _ordered_executor(
@given("a parent plan with {n:d} subplans in sequential mode")
def step_parent_sequential(context: Context, n: int) -> None:
ids = [_S1, _S2, _S3, _S4, _S5][:n]
ids = _ids_for_count(n)
context.subplan_statuses = [_make_status(sid) for sid in ids]
context.subplan_cfg = SubplanConfig(execution_mode=ExecutionMode.SEQUENTIAL)
context.executor_fn = _success_executor
@@ -92,7 +109,7 @@ def step_parent_sequential(context: Context, n: int) -> None:
@given("a parent plan with {n:d} subplans in sequential mode with fail_fast")
def step_parent_sequential_failfast(context: Context, n: int) -> None:
ids = [_S1, _S2, _S3, _S4, _S5][:n]
ids = _ids_for_count(n)
context.subplan_statuses = [_make_status(sid) for sid in ids]
context.subplan_cfg = SubplanConfig(
execution_mode=ExecutionMode.SEQUENTIAL,
@@ -106,7 +123,7 @@ def step_parent_sequential_failfast(context: Context, n: int) -> None:
@given("a parent plan with {n:d} subplan in sequential mode with retry enabled")
def step_parent_sequential_retry(context: Context, n: int) -> None:
ids = [_S1, _S2, _S3, _S4, _S5][:n]
ids = _ids_for_count(n)
context.subplan_statuses = [_make_status(sid) for sid in ids]
context.subplan_cfg = SubplanConfig(
execution_mode=ExecutionMode.SEQUENTIAL,
@@ -140,7 +157,7 @@ def step_first_fails(context: Context, error: str) -> None:
@given("a parent plan with {n:d} subplans in parallel mode with max_parallel {mp:d}")
def step_parent_parallel(context: Context, n: int, mp: int) -> None:
ids = [_S1, _S2, _S3, _S4, _S5][:n]
ids = _ids_for_count(n)
context.subplan_statuses = [_make_status(sid) for sid in ids]
context.subplan_cfg = SubplanConfig(
execution_mode=ExecutionMode.PARALLEL,
@@ -154,7 +171,7 @@ def step_parent_parallel(context: Context, n: int, mp: int) -> None:
@given("a parent plan with {n:d} subplans in parallel mode with fail_fast")
def step_parent_parallel_failfast(context: Context, n: int) -> None:
ids = [_S1, _S2, _S3, _S4, _S5][:n]
ids = _ids_for_count(n)
context.subplan_statuses = [_make_status(sid) for sid in ids]
context.subplan_cfg = SubplanConfig(
execution_mode=ExecutionMode.PARALLEL,
@@ -296,6 +313,12 @@ def step_execute_subplans(context: Context) -> None:
)
@given("parallel execution concurrency tracking is enabled")
def step_parallel_tracking_enabled(context: Context) -> None:
context.concurrency_counter = {"current": 0, "max": 0}
context.concurrency_lock = threading.Lock()
@when("the subplans are executed expecting an error")
def step_execute_expecting_error(context: Context) -> None:
executor_fn = _build_executor(context)
@@ -433,6 +456,12 @@ def step_has_failed_ids(context: Context) -> None:
assert len(result.failed_subplan_ids) > 0
@then("the peak concurrent execution count should not exceed {n:d}")
def step_peak_concurrency_not_exceed(context: Context, n: int) -> None:
peak = context.concurrency_counter["max"]
assert peak <= n, f"Expected peak concurrency <= {n}, got {peak}"
@then("subplan A should have completed before subplan B")
def step_a_before_b(context: Context) -> None:
order = context.execution_order
features/subplan_execution.feature
+8
View File
@@ -47,6 +47,14 @@ Feature: Subplan Execution and Merge
When the subplans are executed
Then all 5 subplans should complete successfully
@parallel
Scenario: Parallel execution scales to 15 subplans while respecting max_parallel
Given a parent plan with 15 subplans in parallel mode with max_parallel 10
And parallel execution concurrency tracking is enabled
When the subplans are executed
Then all 15 subplans should complete successfully
And the peak concurrent execution count should not exceed 10
@parallel
Scenario: Parallel execution with fail_fast cancels remaining on failure
Given a parent plan with 3 subplans in parallel mode with fail_fast
noxfile.py
+4 -1
View File
@@ -22,7 +22,10 @@ def _default_processes() -> int:
cpus = len(os.sched_getaffinity(0)) or 1
except AttributeError:
cpus = os.cpu_count() or 1
return cpus
# Keep default parallelism conservative to avoid timeout/OOM flakes
# under heavy Robot/pabot subprocess fan-out in CI and shared runners.
# Callers can still override with TEST_PROCESSES / --processes.
return min(cpus, 2)
def _behave_parallel_args(posargs: list[str]) -> list[str]:
robot/builtin_adapter.robot
+6 -6
View File
@@ -11,41 +11,41 @@ ${HELPER_SCRIPT} robot/helper_builtin_adapter.py
BuiltinAdapter Discover Returns All Tools
[Documentation] BuiltinAdapter.discover() returns all built-in tool specs
${result}= Run Process ${PYTHON} ${HELPER_SCRIPT} discover
... cwd=${WORKSPACE} on_timeout=kill timeout=30s
... cwd=${WORKSPACE} on_timeout=kill timeout=120s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} discover-ok
BuiltinAdapter Register Populates Registry
[Documentation] BuiltinAdapter.register() populates a ToolRegistry with all tools
${result}= Run Process ${PYTHON} ${HELPER_SCRIPT} register
... cwd=${WORKSPACE} on_timeout=kill timeout=30s
... cwd=${WORKSPACE} on_timeout=kill timeout=120s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} register-ok
BuiltinAdapter Tools Have Builtin Source
[Documentation] All tools registered via BuiltinAdapter have source=builtin
${result}= Run Process ${PYTHON} ${HELPER_SCRIPT} source
... cwd=${WORKSPACE} on_timeout=kill timeout=30s
... cwd=${WORKSPACE} on_timeout=kill timeout=120s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} source-ok
MCP Resource Slot Inference For File Path
[Documentation] MCP infer_resource_slots creates file slot from file_path param
${result}= Run Process ${PYTHON} ${HELPER_SCRIPT} mcp_file
... cwd=${WORKSPACE} on_timeout=kill timeout=30s
... cwd=${WORKSPACE} on_timeout=kill timeout=120s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} mcp-file-ok
MCP Resource Slot Inference For Directory
[Documentation] MCP infer_resource_slots creates directory slot from directory param
${result}= Run Process ${PYTHON} ${HELPER_SCRIPT} mcp_dir
... cwd=${WORKSPACE} on_timeout=kill timeout=30s
... cwd=${WORKSPACE} on_timeout=kill timeout=120s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} mcp-dir-ok
MCP Resource Slot Inference For Repo Path
[Documentation] MCP infer_resource_slots creates repository slot from repo_path param
${result}= Run Process ${PYTHON} ${HELPER_SCRIPT} mcp_repo
... cwd=${WORKSPACE} on_timeout=kill timeout=30s
... cwd=${WORKSPACE} on_timeout=kill timeout=120s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} mcp-repo-ok
robot/cli.robot
+4 -4
View File
@@ -20,7 +20,7 @@ CLI Help Command Performance
${result}= Run Process ${PYTHON} -m cleveragents --help timeout=120s on_timeout=kill
${end_time}= Get Time epoch
${duration}= Evaluate ${end_time} - ${start_time}
Should Be True ${duration} < 60 Help command took too long: ${duration}s
Should Be True ${duration} < 90 Help command took too long: ${duration}s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} AI-powered development assistant
Should Contain ${result.stdout} Usage:
@@ -31,7 +31,7 @@ CLI Version Command Performance
${result}= Run Process ${PYTHON} -m cleveragents --version timeout=120s on_timeout=kill
${end_time}= Get Time epoch
${duration}= Evaluate ${end_time} - ${start_time}
Should Be True ${duration} < 60 Version command took too long: ${duration}s
Should Be True ${duration} < 90 Version command took too long: ${duration}s
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} 1.0.0
@@ -72,7 +72,7 @@ Multiple Commands Benchmark
END
${total_end}= Get Time epoch
${total_duration}= Evaluate ${total_end} - ${total_start}
Should Be True ${total_duration} < 240 Multiple commands took too long: ${total_duration}s
Should Be True ${total_duration} < 360 Multiple commands took too long: ${total_duration}s
CLI Response Time Consistency
[Documentation] Verify consistent response times across multiple runs
@@ -85,4 +85,4 @@ CLI Response Time Consistency
Append To List ${durations} ${duration}
END
${avg_duration}= Evaluate sum(${durations}) / len(${durations})
Should Be True ${avg_duration} < 60 Average response time too high: ${avg_duration}s
Should Be True ${avg_duration} < 90 Average response time too high: ${avg_duration}s
robot/cli_core.robot
+12 -12
View File
@@ -16,20 +16,20 @@ Run CLI With Clean Home
[Documentation] Run a CLI command with a temp HOME to avoid stale config
[Arguments] @{cmd}
${tmpdir}= Evaluate __import__('tempfile').mkdtemp(prefix='cli_core_')
${result}= Run Process @{cmd} timeout=60s env:HOME=${tmpdir}
${result}= Run Process @{cmd} timeout=120s on_timeout=kill env:HOME=${tmpdir}
RETURN ${result}
*** Test Cases ***
Version Command Default Rich Format
[Documentation] Version command with default (rich) format shows version string
${result}= Run Process ${PYTHON} -m cleveragents version timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents version timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} 1.0.0
Should Contain ${result.stdout} CleverAgents
Version Command JSON Format
[Documentation] Version command with --format json returns valid JSON
${result}= Run Process ${PYTHON} -m cleveragents version --format json timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents version --format json timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} "version": "1.0.0"
Should Contain ${result.stdout} "schema": "v3"
@@ -41,21 +41,21 @@ Version Command JSON Format
Version Command Plain Format
[Documentation] Version command with --format plain returns key-value pairs
${result}= Run Process ${PYTHON} -m cleveragents version --format plain timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents version --format plain timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} version: 1.0.0
Should Contain ${result.stdout} schema: v3
Version Command YAML Format
[Documentation] Version command with --format yaml returns YAML
${result}= Run Process ${PYTHON} -m cleveragents version --format yaml timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents version --format yaml timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} version: 1.0.0
Should Contain ${result.stdout} schema: v3
Info Command Default Rich Format
[Documentation] Info command with default (rich) format shows environment details
${result}= Run Process ${PYTHON} -m cleveragents info timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents info timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} Environment
Should Contain ${result.stdout} Runtime
@@ -78,14 +78,14 @@ Info Command Plain Format
Diagnostics Command Default Rich Format
[Documentation] Diagnostics command with default (rich) format runs checks
${result}= Run Process ${PYTHON} -m cleveragents diagnostics timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents diagnostics timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} Checks
Should Contain ${result.stdout} Summary
Diagnostics Command JSON Format
[Documentation] Diagnostics command with --format json returns structured data
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --format json timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --format json timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} "checks"
Should Contain ${result.stdout} "summary"
@@ -96,7 +96,7 @@ Diagnostics Command JSON Format
Diagnostics Command Plain Format
[Documentation] Diagnostics command with --format plain returns key-value pairs
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --format plain timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --format plain timeout=120s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Should Contain ${result.stdout} checks:
Should Contain ${result.stdout} summary:
@@ -104,7 +104,7 @@ Diagnostics Command Plain Format
Diagnostics Command Check Flag Returns Valid Exit Code
[Documentation] Diagnostics --check exits 0 when no critical errors are found.
... Disk-space errors are tolerated since CI runners may have low disk.
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --check --format json timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --check --format json timeout=120s on_timeout=kill
Should Contain ${result.stdout} "checks"
Should Contain ${result.stdout} "has_errors"
# Accept exit code 0 (clean) or 1 if the only error is disk space (CI environment)
@@ -115,8 +115,8 @@ Diagnostics Command Check Flag Returns Valid Exit Code
Diagnostics Command Performance
[Documentation] Diagnostics command completes within acceptable time
${start}= Get Time epoch
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --format json timeout=60s
${result}= Run Process ${PYTHON} -m cleveragents diagnostics --format json timeout=120s on_timeout=kill
${end}= Get Time epoch
${duration}= Evaluate ${end} - ${start}
Should Be True ${duration} < 30 Diagnostics took too long: ${duration}s
Should Be True ${duration} < 90 Diagnostics took too long: ${duration}s
Should Be Equal As Integers ${result.rc} 0
robot/cli_plan_context_commands.robot
+4 -4
View File
@@ -7,7 +7,7 @@ Library Process
Library String
Suite Setup Setup Test Environment
Suite Teardown Cleanup Test Environment
Test Timeout 300 seconds
Test Timeout 900 seconds
*** Variables ***
# ${PYTHON} will be set in Setup Test Environment from common.resource
@@ -21,7 +21,7 @@ Initialize New Project
[Setup] Setup Test Directory
${result}= Run Process ${PYTHON} -m cleveragents init ${PROJECT_NAME}
... cwd=${TEST_DIR} env:CLEVERAGENTS_AUTO_APPLY_MIGRATIONS=true stderr=STDOUT timeout=120s on_timeout=kill
... cwd=${TEST_DIR} env:CLEVERAGENTS_AUTO_APPLY_MIGRATIONS=true stderr=STDOUT timeout=300s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0 Init failed: ${result.stdout}
Should Exist ${TEST_DIR}${/}.cleveragents
@@ -39,7 +39,7 @@ Add Files To Context
# Add files to context
${result}= Run Process ${PYTHON} -m cleveragents context-load test.py main.py
... cwd=${TEST_DIR} timeout=120s on_timeout=kill
... cwd=${TEST_DIR} timeout=300s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
@@ -265,7 +265,7 @@ Initialize Test Project
[Documentation] Initialize a test project
Setup Test Directory
${result}= Run Process ${PYTHON} -m cleveragents init ${PROJECT_NAME}
... cwd=${TEST_DIR} timeout=120s on_timeout=kill
... cwd=${TEST_DIR} timeout=300s on_timeout=kill
Should Be Equal As Integers ${result.rc} 0
Initialize Test Project With Plan
robot/core_cli_commands.robot
+1 -1
View File
@@ -7,7 +7,7 @@ Library Collections
Resource discovery_common.resource
Suite Setup Setup Test Environment
Suite Teardown Cleanup Test Environment
Test Timeout 300 seconds
Test Timeout 900 seconds
*** Variables ***
${PYTHON} python
robot/database_integration.robot
+1 -1
View File
@@ -759,7 +759,7 @@ Run Python Script
# Create File writes to it (avoids leaking an open descriptor).
${temp_file}= Evaluate (lambda t: (__import__('os').close(t[0]), t[1])[-1])(__import__('tempfile').mkstemp(suffix='.py', dir='/tmp'))
Create File ${temp_file} ${full_code}
${result}= Run Process ${PYTHON} ${temp_file} timeout=60s stderr=STDOUT env:PYTHONWARNINGS=ignore env:PYTHONDONTWRITEBYTECODE=1
${result}= Run Process ${PYTHON} ${temp_file} timeout=180s stderr=STDOUT env:PYTHONWARNINGS=ignore env:PYTHONDONTWRITEBYTECODE=1
Remove File ${temp_file}
# Check if process failed and log stderr if present
IF ${result.rc} != 0
robot/helper_cli_consistency.py
+1 -1
View File
@@ -82,7 +82,7 @@ def _run_error_script(python_path: str, script: str) -> dict[str, object]:
[python_path, "-c", script],
capture_output=True,
text=True,
timeout=30,
timeout=90,
)
return {
"rc": result.returncode,
robot/helper_container_resolve_crash.py
+1 -1
View File
@@ -205,7 +205,7 @@ def _run_and_verify(
*args,
workspace=str(Path.cwd()),
env_extra={"CLEVERAGENTS_DATABASE_URL": ctx.database_url},
timeout=25,
timeout=120,
)
output = (result.stdout or "") + (result.stderr or "")
lowered = output.lower()
robot/helper_tdd_plan_explain_plan_id.py
+65 -30
View File
@@ -14,8 +14,10 @@ the Robot side handles pass/fail inversion while the bug remains open.
from __future__ import annotations
import os
import shutil
import subprocess
import sys
import tempfile
from collections.abc import Callable
from pathlib import Path
from typing import NoReturn
@@ -30,7 +32,11 @@ for _p in (_SRC, _ROBOT):
from ulid import ULID # noqa: E402
from cleveragents.application.container import get_container # noqa: E402
from cleveragents.application.container import ( # noqa: E402
get_container,
reset_container,
)
from cleveragents.config.settings import Settings # noqa: E402
from cleveragents.domain.models.core.decision import DecisionType # noqa: E402
# ---------------------------------------------------------------------------
@@ -51,6 +57,27 @@ def _make_subprocess_env() -> dict[str, str]:
return env
def _setup_isolated_home() -> tuple[str, str | None]:
"""Create and activate an isolated CLEVERAGENTS_HOME for this run."""
tmp_home = tempfile.mkdtemp(prefix="tdd_plan_explain_968_")
previous_home = os.environ.get("CLEVERAGENTS_HOME")
os.environ["CLEVERAGENTS_HOME"] = tmp_home
reset_container()
Settings._instance = None
return tmp_home, previous_home
def _restore_isolated_home(tmp_home: str, previous_home: str | None) -> None:
"""Restore prior environment and clean up temporary home directory."""
if previous_home is not None:
os.environ["CLEVERAGENTS_HOME"] = previous_home
else:
os.environ.pop("CLEVERAGENTS_HOME", None)
reset_container()
Settings._instance = None
shutil.rmtree(tmp_home, ignore_errors=True)
def _setup_plan_with_decisions() -> str:
"""Create a plan_id and record decisions against it.
@@ -132,28 +159,32 @@ def explain_with_plan_id() -> None:
back to looking up decisions for the plan via ``list_decisions(plan_id)``
and explain the root decision.
"""
plan_id: str = _setup_plan_with_decisions()
result: subprocess.CompletedProcess[str] = _run_plan_explain(plan_id)
tmp_home, previous_home = _setup_isolated_home()
try:
plan_id: str = _setup_plan_with_decisions()
result: subprocess.CompletedProcess[str] = _run_plan_explain(plan_id)
if result.returncode != 0:
_fail(
f"plan explain {plan_id} exited with rc={result.returncode}. "
f"stdout: {result.stdout}\n"
f"stderr: {result.stderr}\n"
f"Bug #968: explain treats the argument as a decision_id, "
f"get_decision(plan_id) raises DecisionNotFoundError, command fails."
)
if result.returncode != 0:
_fail(
f"plan explain {plan_id} exited with rc={result.returncode}. "
f"stdout: {result.stdout}\n"
f"stderr: {result.stderr}\n"
f"Bug #968: explain treats the argument as a decision_id, "
f"get_decision(plan_id) raises DecisionNotFoundError, command fails."
)
# Verify the output contains decision-related content — both keywords
# must be present (mirrors the AND-based assertion in the Behave test).
combined: str = result.stdout + result.stderr
if "decision" not in combined.lower() or "question" not in combined.lower():
_fail(
f"plan explain output does not contain decision details. "
f"stdout: {result.stdout}"
)
# Verify the output contains decision-related content — both keywords
# must be present (mirrors the AND-based assertion in the Behave test).
combined: str = result.stdout + result.stderr
if "decision" not in combined.lower() or "question" not in combined.lower():
_fail(
f"plan explain output does not contain decision details. "
f"stdout: {result.stdout}"
)
print("tdd-plan-explain-plan-id-ok")
print("tdd-plan-explain-plan-id-ok")
finally:
_restore_isolated_home(tmp_home, previous_home)
def explain_plan_id_shows_question() -> None:
@@ -162,19 +193,23 @@ def explain_plan_id_shows_question() -> None:
Bug #968: Since the command fails with rc=1 before any output is
rendered, the root decision question is never displayed.
"""
plan_id: str = _setup_plan_with_decisions()
result: subprocess.CompletedProcess[str] = _run_plan_explain(plan_id)
tmp_home, previous_home = _setup_isolated_home()
try:
plan_id: str = _setup_plan_with_decisions()
result: subprocess.CompletedProcess[str] = _run_plan_explain(plan_id)
if result.returncode != 0:
_fail(
f"plan explain {plan_id} exited with rc={result.returncode}. "
f"Bug #968: command fails before rendering any output."
)
if result.returncode != 0:
_fail(
f"plan explain {plan_id} exited with rc={result.returncode}. "
f"Bug #968: command fails before rendering any output."
)
if "What should we build?" not in result.stdout:
_fail(f"Expected root decision question in output. stdout: {result.stdout}")
if "What should we build?" not in result.stdout:
_fail(f"Expected root decision question in output. stdout: {result.stdout}")
print("tdd-plan-explain-plan-id-question-ok")
print("tdd-plan-explain-plan-id-question-ok")
finally:
_restore_isolated_home(tmp_home, previous_home)
# ---------------------------------------------------------------------------
robot/m3_e2e_verification.robot
+10 -10
View File
@@ -26,7 +26,7 @@ Plan Execution Generates Decisions During Strategize
... Validates: plan use + plan execute generate decisions
... during Strategize phase.
[Tags] success_criteria decision_recording
${result}= Run Process ${PYTHON} ${HELPER} plan-generates-decisions cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} plan-generates-decisions cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -39,7 +39,7 @@ Decision Tree View Via Plan Tree
...
... Validates: plan tree displays the decision tree correctly.
[Tags] success_criteria decision_tree
${result}= Run Process ${PYTHON} ${HELPER} decision-tree-view cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} decision-tree-view cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -52,7 +52,7 @@ Decision Explain Shows Full Context
...
... Validates: plan explain shows full decision context.
[Tags] success_criteria decision_explain
${result}= Run Process ${PYTHON} ${HELPER} decision-explain cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} decision-explain cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -65,7 +65,7 @@ Invariant Add And List Via CLI And Service
...
... Validates: invariant add and invariant list CLI commands.
[Tags] success_criteria invariant_management
${result}= Run Process ${PYTHON} ${HELPER} invariant-add-list cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} invariant-add-list cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -80,7 +80,7 @@ Correction Dry Run Via Plan Correct
... Validates: plan correct with --dry-run performs
... impact analysis without modifying state.
[Tags] success_criteria correction_dry_run
${result}= Run Process ${PYTHON} ${HELPER} correction-dry-run cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} correction-dry-run cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -94,7 +94,7 @@ Correction Live Revert Executes And Re-Creates Decisions
... Validates: plan correct with --mode revert executes
... live correction.
[Tags] success_criteria correction_live_revert
${result}= Run Process ${PYTHON} ${HELPER} correction-live-revert cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} correction-live-revert cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -108,7 +108,7 @@ Decisions Recorded With Full Context Snapshot
... Technical criterion: decisions recorded during
... Strategize with full context snapshot.
[Tags] technical_criteria context_snapshot
${result}= Run Process ${PYTHON} ${HELPER} decisions-context-snapshot cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} decisions-context-snapshot cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -122,7 +122,7 @@ Decision Tree Persists To Database And Renders
... Technical criterion: decision tree persists to
... database and renders correctly.
[Tags] technical_criteria persistence
${result}= Run Process ${PYTHON} ${HELPER} decision-tree-persistence cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} decision-tree-persistence cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -137,7 +137,7 @@ Correction Revert Re-Executes From Decision Point
... Technical criterion: correction in revert mode
... re-executes from decision point.
[Tags] technical_criteria correction_reexecution
${result}= Run Process ${PYTHON} ${HELPER} correction-revert-reexecutes cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} correction-revert-reexecutes cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -153,7 +153,7 @@ Invariants Enforced During Strategize
... Technical criterion: invariants are enforced
... during strategize.
[Tags] technical_criteria invariant_enforcement
${result}= Run Process ${PYTHON} ${HELPER} invariants-enforced-strategize cwd=${WORKSPACE} timeout=120s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} invariants-enforced-strategize cwd=${WORKSPACE} timeout=300s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
robot/tdd_actor_list_no_db_update.robot
+2 -2
View File
@@ -19,7 +19,7 @@ TDD Actor List Does Not Call Upsert Actor
... ``ensure_built_in_actors()`` which writes to the DB.
[Tags] tdd_bug tdd_bug_797
${result}= Run Process ${PYTHON} ${HELPER} check-no-upsert
... cwd=${WORKSPACE} timeout=30s on_timeout=kill
... cwd=${WORKSPACE} timeout=120s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -32,7 +32,7 @@ TDD Actor List Does Not Call Set Default Actor
... call ``set_default_actor()`` — another DB write.
[Tags] tdd_bug tdd_bug_797
${result}= Run Process ${PYTHON} ${HELPER} check-no-set-default
... cwd=${WORKSPACE} timeout=30s on_timeout=kill
... cwd=${WORKSPACE} timeout=120s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
robot/tdd_plan_apply_yes_flag.robot
+2 -2
View File
@@ -16,7 +16,7 @@ ${HELPER} ${CURDIR}/helper_tdd_plan_apply_yes_flag.py
TDD Plan Apply Yes Long Flag Via CLI
[Documentation] Verify that ``lifecycle-apply --yes`` is recognised
[Tags] tdd_issue tdd_issue_932
${result}= Run Process ${PYTHON} ${HELPER} check-yes-long cwd=${WORKSPACE} timeout=30s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} check-yes-long cwd=${WORKSPACE} timeout=120s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -25,7 +25,7 @@ TDD Plan Apply Yes Long Flag Via CLI
TDD Plan Apply Yes Short Flag Via CLI
[Documentation] Verify that ``lifecycle-apply -y`` is recognised
[Tags] tdd_issue tdd_issue_932
${result}= Run Process ${PYTHON} ${HELPER} check-yes-short cwd=${WORKSPACE} timeout=30s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} check-yes-short cwd=${WORKSPACE} timeout=120s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
robot/tdd_plan_correct_plan_id.robot
+2 -2
View File
@@ -22,7 +22,7 @@ TDD Plan Correct Accepts Plan ID As Positional Argument Revert Mode
... argument with --mode revert. Bug #969: the code currently
... uses the plan_id as target_decision_id directly.
[Tags] tdd_issue tdd_issue_969
${result}= Run Process ${PYTHON} ${HELPER} plan-correct-with-plan-id cwd=${WORKSPACE} timeout=30s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} plan-correct-with-plan-id cwd=${WORKSPACE} timeout=120s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -35,7 +35,7 @@ TDD Plan Correct Accepts Plan ID As Positional Argument Append Mode
... target_decision_id resolution before mode branching, so both
... revert and append modes are affected.
[Tags] tdd_issue tdd_issue_969
${result}= Run Process ${PYTHON} ${HELPER} plan-correct-append-with-plan-id cwd=${WORKSPACE} timeout=30s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} plan-correct-append-with-plan-id cwd=${WORKSPACE} timeout=120s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
robot/tdd_plan_explain_plan_id.robot
+2 -2
View File
@@ -16,7 +16,7 @@ TDD Plan Explain Succeeds With Plan ID
... when given a plan ID that has associated decisions.
... Bug #968: the command currently exits with rc=1.
[Tags] tdd_issue tdd_issue_968
${result}= Run Process ${PYTHON} ${HELPER} explain-with-plan-id cwd=${WORKSPACE} timeout=60s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} explain-with-plan-id cwd=${WORKSPACE} timeout=180s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
@@ -27,7 +27,7 @@ TDD Plan Explain With Plan ID Shows Root Question
... the root decision question when given a plan ID.
... Bug #968: the command fails before rendering any output.
[Tags] tdd_issue tdd_issue_968
${result}= Run Process ${PYTHON} ${HELPER} explain-plan-id-shows-question cwd=${WORKSPACE} timeout=60s on_timeout=kill
${result}= Run Process ${PYTHON} ${HELPER} explain-plan-id-shows-question cwd=${WORKSPACE} timeout=180s on_timeout=kill
Log ${result.stdout}
Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
src/cleveragents/application/services/decomposition_service.py
+10 -5
View File
@@ -206,9 +206,13 @@ class DecompositionService:
estimated = sum(estimate_tokens_for_path(f) for f in files)
# Leaf conditions
is_leaf = depth >= config.max_depth or (
len(files) <= config.max_files_per_subplan
and estimated <= config.max_tokens_per_subplan
# M6 requires deep hierarchical decomposition (4+ levels) for
# large plans. To preserve this behavior, we only stop early when
# we hit max_depth or the workset is trivially small; otherwise we
# keep partitioning even when a cluster is already under the max
# file/token bounds.
is_leaf = (
depth >= config.max_depth or len(files) <= config.min_files_per_subplan
)
node_id = _next_node_id()
@@ -244,8 +248,9 @@ class DecompositionService:
)
strategy = ClusterStrategy.SIZE
# Fallback: single cluster with warning
if not clusters:
# Fallback: no clusters or a single cluster that covers all files
# (non-progress guard - recursing with the same set would loop).
if not clusters or (len(clusters) == 1 and len(clusters[0]) == len(files)):
logger.warning(
"decomposition_fallback",
extra={"file_count": len(files), "depth": depth},