mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
e3570b444f
Smoke-8 follow-up. Two issues in _write_agent_briefing: 1. _build_tool_load_block was scraping role prompts for a "## Load on spawn" section that doesn't exist in any role file. Returned "" for every role → no ToolSearch directive in the briefing. Combined with weak models skipping the system-prompt-layer directive (#144), the agent's first action was Edit → "not enabled in this context." Fix: per-role tool list lives in the orchestrator (mirrors factories._base.py). Pre-renders the directive directly. developer and documenter get Edit + Write; QA/PMs/board get the common read-only set. 7 tests pin the contract. 2. The briefing's "Terminal tools (how to exit cleanly)" section still listed pre-gateway verb names: roboco_agent_idle, roboco_task_substitute, roboco_task_escalate, roboco_task_submit_qa, _qa_pass/fail, _docs_complete, _complete. Same rename pattern as #145's _TERMINAL_TOOLS set. Updated to: i_am_idle, i_am_blocked, unclaim, i_am_done, pass, fail, i_documented, complete, submit_up, escalate_up, escalate_to_ceo. The agent now reads the same directive in two places (system prompt + session briefing) — the second touch point catches weak models that skip the first.
84 lines
2.9 KiB
Python
84 lines
2.9 KiB
Python
"""Smoke-8: briefing's _build_tool_load_block emits the ToolSearch directive
|
|
without depending on a "## Load on spawn" section in the role file.
|
|
|
|
The previous implementation scraped role prompts for that marker; since
|
|
no role file had it, the function returned "" and the briefing showed
|
|
agents no tool-load instruction. Combined with weak models skipping the
|
|
system-prompt directive, the agent went straight to Edit and hit "not
|
|
enabled in this context."
|
|
|
|
Fix: per-role tool list lives in the orchestrator (mirrors the
|
|
factories layer). Pre-renders the directive directly — no file scrape.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
from unittest.mock import patch
|
|
|
|
from roboco.runtime.orchestrator import AgentOrchestrator
|
|
|
|
|
|
def _orch() -> AgentOrchestrator:
|
|
with patch.object(AgentOrchestrator, "__init__", return_value=None):
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
orch._TOOL_LOAD_CACHE = {}
|
|
return orch
|
|
|
|
|
|
def test_developer_directive_includes_edit_and_write() -> None:
|
|
block = _orch()._build_tool_load_block("developer")
|
|
assert "First action required" in block
|
|
assert "ToolSearch" in block
|
|
assert "Edit" in block
|
|
assert "Write" in block
|
|
|
|
|
|
def test_documenter_directive_includes_edit_and_write() -> None:
|
|
block = _orch()._build_tool_load_block("documenter")
|
|
assert "Edit" in block
|
|
assert "Write" in block
|
|
|
|
|
|
def test_qa_directive_excludes_edit_and_write() -> None:
|
|
block = _orch()._build_tool_load_block("qa")
|
|
assert "First action required" in block
|
|
# The ToolSearch line itself: pull the comma list to be precise about
|
|
# which tools are listed (substring match would catch "TodoWrite").
|
|
match = re.search(r'select:([^"]+)"', block)
|
|
assert match is not None
|
|
tools = match.group(1).split(",")
|
|
assert "Edit" not in tools
|
|
assert "Write" not in tools
|
|
assert "Read" in tools
|
|
assert "Bash" in tools
|
|
|
|
|
|
def test_pm_directives_exclude_edit_and_write() -> None:
|
|
for role in ("main_pm", "cell_pm", "product_owner", "head_marketing", "auditor"):
|
|
block = _orch()._build_tool_load_block(role)
|
|
match = re.search(r'select:([^"]+)"', block)
|
|
assert match is not None
|
|
tools = match.group(1).split(",")
|
|
assert "Edit" not in tools, f"{role} must not list Edit"
|
|
assert "Write" not in tools, f"{role} must not list Write"
|
|
|
|
|
|
def test_unknown_role_returns_empty() -> None:
|
|
"""No directive for unknown roles (defensive)."""
|
|
block = _orch()._build_tool_load_block("nonexistent")
|
|
assert block == ""
|
|
|
|
|
|
def test_directive_warns_about_failure_mode() -> None:
|
|
block = _orch()._build_tool_load_block("developer")
|
|
assert "Edit exists but is not enabled" in block
|
|
|
|
|
|
def test_role_cache_works() -> None:
|
|
orch = _orch()
|
|
first = orch._build_tool_load_block("developer")
|
|
# Second call hits the cache (same return).
|
|
second = orch._build_tool_load_block("developer")
|
|
assert first is second # same string object
|