Echo Core devine planning agent: poartă o conversație multi-fază cu Marius folosind skill-urile gstack (/office-hours → /plan-ceo-review → /plan-eng-review → /plan-design-review opt) și produce final-plan.md în ~/workspace/<slug>/scripts/ralph/, gata să fie consumat de Ralph PRD generator (W3) noaptea. Decizii arhitecturale (din eng review + spike findings): - PlanningSession ca clasă SEPARATĂ de chat-ul main (NU mode=string param) — separation explicit. claude_session.py rămâne strict pentru chat; planning trăiește în src/planning_session.py + src/planning_orchestrator.py. Inheritance literală nu se aplică (claude_session.py expune funcții module-level, nu o clasă) — separation e satisfacută prin module distinct. - Fresh subprocess PER skill phase, NU single resumed session — phase-urile coordinează via disk artifacts (gstack convention în ~/.gstack/projects/<slug>/). Avoids context window growth. - --max-turns 20 default + retry pe error_max_turns la --max-turns 30. Spike a arătat că prompt-uri complexe pot exploda turn budget-ul. - approved-tasks.json schema extins cu planning_session_id + final_plan_path (Status flow: pending → planning → approved → running → complete). - State separat în sessions/planning.json (NU active.json), keyed pe (adapter, channel_id) pentru re-resume la restart echo-core. Trigger-e: - Discord: slash command /plan <slug> [descriere] cu autocomplete pe pending, buton "🧠 Planifică" în RalphProjectView, și /cancel slash command. - Telegram: /plan + /cancel commands, plus buton "🧠 Planifică" în ralph project keyboard. - Router: state-aware routing — dacă chat-ul e în planning, mesajele plain trec la PlanningOrchestrator.respond() prin --resume; /cancel revine la status pending; /advance / "Continuă faza" advance fază nouă (fresh subprocess); /finalize sau "Dau drumul" promote la status approved. Discord defer pattern: toate butoanele noi (PlanningActiveView, PlanningFinalView, "🧠 Planifică") apelează await interaction.response.defer(ephemeral=True) ÎNAINTE de orice IO — evită "Interaction failed" pe IO >3s. UX strings warm + colaborativ (per design review): "🧠 Pornesc planning pentru ...", "Răspunde aici", "Continuă faza", "Dau drumul tonight", "Anulează" — niciun "Submit/Approve/Cancel" generic. Tests: 23 noi (test_planning_session, test_planning_orchestrator, test_router_planning) — toate pass. Mock pe _run_claude pentru a evita subprocess Claude real în CI. Files new: prompts/planning_agent.md src/planning_session.py src/planning_orchestrator.py tests/test_planning_session.py tests/test_planning_orchestrator.py tests/test_router_planning.py Files modified: src/claude_session.py — _run_claude(cwd=...) optional + surface subtype/is_error src/router.py — state-aware routing, start_planning_session, planning_advance/approve/cancel, _ralph_propose schema cu planning_session_id + final_plan_path src/adapters/discord_bot.py — /plan + /cancel slash commands; planning views imported src/adapters/discord_views.py — PlanningActiveView, PlanningFinalView, "Planifică" button în RalphProjectView, _split_chunks helper src/adapters/telegram_bot.py — /plan + /cancel handlers, callback_ralph extins cu plan/planadvance/plancancel/planapprove, planning keyboards Status testelor pe modulele atinse: 75 passed, 0 failed (test_claude_session security_section preexistent — neatins). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
279 lines
10 KiB
Python
279 lines
10 KiB
Python
"""Tests for src/planning_session.py — PlanningSession + state persistence."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from src import planning_session
|
|
from src.planning_session import (
|
|
PHASE_NEEDS_INPUT_MARKER,
|
|
PHASE_READY_MARKER,
|
|
PlanningSession,
|
|
_channel_key,
|
|
build_planning_system_prompt,
|
|
clear_planning_state,
|
|
get_planning_state,
|
|
is_in_planning,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Fixtures
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.fixture
|
|
def tmp_planning_state(tmp_path, monkeypatch):
|
|
"""Redirect planning state file into a tmp dir for each test."""
|
|
fake_sessions_dir = tmp_path / "sessions"
|
|
fake_sessions_dir.mkdir()
|
|
fake_state = fake_sessions_dir / "planning.json"
|
|
monkeypatch.setattr(planning_session, "SESSIONS_DIR", fake_sessions_dir)
|
|
monkeypatch.setattr(planning_session, "PLANNING_STATE_FILE", fake_state)
|
|
yield fake_state
|
|
|
|
|
|
@pytest.fixture
|
|
def fake_workspace(tmp_path, monkeypatch):
|
|
"""Pretend ~/workspace/<slug>/ exists so PlanningSession.cwd resolves."""
|
|
workspace = tmp_path / "workspace"
|
|
workspace.mkdir()
|
|
(workspace / "demo").mkdir()
|
|
monkeypatch.setattr(planning_session, "WORKSPACE_ROOT", workspace)
|
|
yield workspace
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# build_planning_system_prompt
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestBuildPlanningSystemPrompt:
|
|
def test_substitutes_slug_phase_description(self):
|
|
prompt = build_planning_system_prompt(
|
|
slug="demo", description="Add filter X", phase="/office-hours"
|
|
)
|
|
# Even if the prompt template differs, the values must appear at least
|
|
# once each.
|
|
assert "demo" in prompt
|
|
assert "Add filter X" in prompt
|
|
assert "/office-hours" in prompt
|
|
|
|
def test_returns_empty_when_template_missing(self, tmp_path, monkeypatch):
|
|
monkeypatch.setattr(
|
|
planning_session, "PLANNING_PROMPT_FILE", tmp_path / "missing.md"
|
|
)
|
|
assert build_planning_system_prompt("a", "b", "/x") == ""
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# state get/set/clear
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestPlanningState:
|
|
def test_clear_returns_false_when_absent(self, tmp_planning_state):
|
|
assert clear_planning_state("discord", "ch-1") is False
|
|
|
|
def test_get_returns_none_when_absent(self, tmp_planning_state):
|
|
assert get_planning_state("discord", "ch-1") is None
|
|
assert is_in_planning("discord", "ch-1") is False
|
|
|
|
def test_persist_and_recover(self, tmp_planning_state, fake_workspace):
|
|
# Build a session WITHOUT actually invoking claude — call _persist directly.
|
|
sess = PlanningSession(
|
|
slug="demo",
|
|
description="desc",
|
|
phase="/office-hours",
|
|
channel_id="ch-1",
|
|
adapter="discord",
|
|
session_id="sess-uuid-1",
|
|
)
|
|
sess._last_response = "hello world " + PHASE_NEEDS_INPUT_MARKER
|
|
sess._last_subtype = "success"
|
|
sess._persist(action="start", cost_usd=0.42)
|
|
|
|
assert is_in_planning("discord", "ch-1") is True
|
|
state = get_planning_state("discord", "ch-1")
|
|
assert state is not None
|
|
assert state["slug"] == "demo"
|
|
assert state["session_id"] == "sess-uuid-1"
|
|
assert state["phase"] == "/office-hours"
|
|
assert state["last_subtype"] == "success"
|
|
assert "hello world" in state["last_text_excerpt"]
|
|
|
|
recovered = PlanningSession.from_state("discord", "ch-1")
|
|
assert recovered is not None
|
|
assert recovered.slug == "demo"
|
|
assert recovered.session_id == "sess-uuid-1"
|
|
assert recovered.phase == "/office-hours"
|
|
|
|
assert clear_planning_state("discord", "ch-1") is True
|
|
assert get_planning_state("discord", "ch-1") is None
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# is_phase_ready
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestIsPhaseReady:
|
|
def test_returns_true_when_marker_present(self, fake_workspace):
|
|
sess = PlanningSession("demo", "d", "/x", "ch", session_id="abc")
|
|
sess._last_response = f"some text {PHASE_READY_MARKER}"
|
|
assert sess.is_phase_ready() is True
|
|
|
|
def test_returns_false_when_marker_absent(self, fake_workspace):
|
|
sess = PlanningSession("demo", "d", "/x", "ch", session_id="abc")
|
|
sess._last_response = "some text without marker"
|
|
assert sess.is_phase_ready() is False
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# cwd resolution
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestCwd:
|
|
def test_workspace_dir_used_when_present(self, fake_workspace):
|
|
sess = PlanningSession("demo", "d", "/x", "ch")
|
|
assert sess.cwd == fake_workspace / "demo"
|
|
|
|
def test_falls_back_to_project_root_when_missing(
|
|
self, fake_workspace, monkeypatch
|
|
):
|
|
sess = PlanningSession("nonexistent-slug", "d", "/x", "ch")
|
|
# Falls back to PROJECT_ROOT
|
|
assert sess.cwd == planning_session.PROJECT_ROOT
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# command construction
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestBuildCmd:
|
|
def test_start_includes_skill_phase_and_max_turns(self, fake_workspace):
|
|
sess = PlanningSession("demo", "Add filter", "/office-hours", "ch")
|
|
cmd = sess._build_cmd(
|
|
"/office-hours Add filter",
|
|
resume=None,
|
|
max_turns=20,
|
|
with_system_prompt=False,
|
|
)
|
|
assert cmd[0:3] == [planning_session.CLAUDE_BIN, "-p", "/office-hours Add filter"]
|
|
assert "--max-turns" in cmd
|
|
assert "20" in cmd
|
|
assert "--output-format" in cmd
|
|
assert "stream-json" in cmd
|
|
assert "--dangerously-skip-permissions" in cmd
|
|
# No --resume on a fresh start
|
|
assert "--resume" not in cmd
|
|
|
|
def test_resume_includes_resume_flag(self, fake_workspace):
|
|
sess = PlanningSession(
|
|
"demo", "Add filter", "/office-hours", "ch", session_id="abc"
|
|
)
|
|
cmd = sess._build_cmd(
|
|
"user reply",
|
|
resume="abc",
|
|
max_turns=20,
|
|
with_system_prompt=False,
|
|
)
|
|
assert "--resume" in cmd
|
|
assert "abc" in cmd
|
|
|
|
def test_with_system_prompt_appends_flag(self, fake_workspace, tmp_path, monkeypatch):
|
|
# Create a tiny prompt file so build_planning_system_prompt returns text.
|
|
fake = tmp_path / "planning_agent.md"
|
|
fake.write_text("phase={phase} slug={slug}", encoding="utf-8")
|
|
monkeypatch.setattr(planning_session, "PLANNING_PROMPT_FILE", fake)
|
|
sess = PlanningSession("demo", "d", "/office-hours", "ch")
|
|
cmd = sess._build_cmd(
|
|
"prompt", resume=None, max_turns=20, with_system_prompt=True
|
|
)
|
|
assert "--system-prompt" in cmd
|
|
idx = cmd.index("--system-prompt")
|
|
assert "phase=/office-hours" in cmd[idx + 1]
|
|
assert "slug=demo" in cmd[idx + 1]
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# start() — integration-flavoured, mocks _run_claude
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestStart:
|
|
def test_persists_session_id_and_response(
|
|
self, tmp_planning_state, fake_workspace
|
|
):
|
|
fake_result = {
|
|
"result": "Bună! Câteva întrebări… " + PHASE_NEEDS_INPUT_MARKER,
|
|
"session_id": "claude-uuid-99",
|
|
"usage": {"input_tokens": 1000, "output_tokens": 200},
|
|
"total_cost_usd": 0.55,
|
|
"subtype": "success",
|
|
"is_error": False,
|
|
}
|
|
with patch("src.planning_session._run_claude", return_value=fake_result) as mock_run:
|
|
sess = PlanningSession.start(
|
|
slug="demo",
|
|
description="Add filter X",
|
|
phase="/office-hours",
|
|
channel_id="ch-1",
|
|
adapter="discord",
|
|
)
|
|
mock_run.assert_called_once()
|
|
# cwd kw passed
|
|
_, kwargs = mock_run.call_args
|
|
assert "cwd" in kwargs
|
|
assert sess.session_id == "claude-uuid-99"
|
|
assert "Bună" in sess.last_response
|
|
state = get_planning_state("discord", "ch-1")
|
|
assert state["session_id"] == "claude-uuid-99"
|
|
assert state["slug"] == "demo"
|
|
assert state["phase"] == "/office-hours"
|
|
|
|
def test_retries_on_error_max_turns(self, tmp_planning_state, fake_workspace):
|
|
# First call returns error_max_turns with no session_id; second returns success.
|
|
first = {
|
|
"result": "deep tool use",
|
|
"session_id": "",
|
|
"usage": {},
|
|
"total_cost_usd": 0.6,
|
|
"subtype": "error_max_turns",
|
|
"is_error": True,
|
|
}
|
|
second = {
|
|
"result": "now I have a question",
|
|
"session_id": "claude-uuid-2",
|
|
"usage": {},
|
|
"total_cost_usd": 0.7,
|
|
"subtype": "success",
|
|
"is_error": False,
|
|
}
|
|
with patch(
|
|
"src.planning_session._run_claude", side_effect=[first, second]
|
|
) as mock_run:
|
|
sess = PlanningSession.start(
|
|
slug="demo",
|
|
description="Add filter X",
|
|
phase="/office-hours",
|
|
channel_id="ch-1",
|
|
adapter="discord",
|
|
)
|
|
assert mock_run.call_count == 2
|
|
assert sess.session_id == "claude-uuid-2"
|
|
# Second call uses RETRY_MAX_TURNS
|
|
second_args = mock_run.call_args_list[1][0][0]
|
|
assert "30" in second_args # RETRY_MAX_TURNS
|
|
|
|
def test_respond_requires_session_id(self, fake_workspace):
|
|
sess = PlanningSession("demo", "d", "/x", "ch") # no session_id
|
|
with pytest.raises(RuntimeError):
|
|
sess.respond("hello")
|