External/roboco
1
0
Fork 0
mirror of https://github.com/rennf93/roboco.git synced 2026-08-03 07:23:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix: open findings cleanup (#122)

Browse Source 
* refactor(usage): remove the unconsumed per-agent USAGE_UPDATE event

USAGE_UPDATE was published per active agent each sweep, bridged, and
broadcast to /ws/system, but no panel client ever consumed it — the
dashboard reads only the aggregate USAGE_SNAPSHOT. Every emission was
wasted event-bus and WebSocket traffic.

Drop the UsageUpdate payload, publish_usage_update and its throttle, the
EventType member, and the bridge subscription. Keep USAGE_SNAPSHOT, which
already carries the per-agent breakdown, so no live data is lost.

* refactor(prompter): remove the legacy local-LLM HTTP endpoints

The panel uses only the live SDK-intake path (/prompter/live/*); the legacy
/prompter/chat, /draft and /sessions/* endpoints — backed by the local Ollama
LLM with hardcoded prompts — had no remaining caller. Remove the router, its
mount in app.py, and its integration test. The live router and the shared
draft-confirmation service are untouched.

* refactor(prompter): drop the dead legacy local-LLM service + schemas

With the legacy HTTP endpoints gone, the local-LLM chat/draft/session methods,
their prompt constants, the ConfirmOverrides/TurnResult dataclasses, and the
entire prompter schema module had no production caller (only their own tests).
Remove them, keeping the live-intake path: create_task_from_draft /
confirm_live_draft, the enum/priority/team coercion, and the pure
description/readiness helpers.

* refactor(agents): stop granting the Task sub-agent tool to roles

Every agent role was granted the built-in Task tool, but no role prompt or
workflow uses it and there are no custom sub-agent definitions — so a Task call
only spawns a context-blind generic sub-agent that burns budget (ToolSearch,
the comment's stated use, is MCP-only and not callable in agent containers).

Drop Task from all three grant points in lockstep: the --tools spawn flag and
both _ROLE_BUILTIN_TOOLS maps (system-prompt + briefing layers), with a
regression guard added to each layer's test.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
This commit is contained in:
Renzo F
2026-06-12 23:10:21 +02:00
committed by GitHub
co-authored by Renn F
parent cdde3b256e
commit 718d7dd83e
16 changed files with 84 additions and 2941 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/unit/agents/test_tool_load_directive_layer.py
+18
View File
@@ -95,6 +95,24 @@ def test_pm_blocks_exclude_edit_and_write() -> None:
)
def test_no_role_is_granted_the_task_subagent_tool() -> None:
"""Task (sub-agent dispatch) is dropped from the built-in tool grant.
No role prompt or workflow uses Task and there are no custom sub-agent
definitions, so a Task call only spawns a context-blind generic sub-agent
that burns budget. The tools-ready line must not advertise it for any role.
"""
for role in (
AgentRole.DEVELOPER,
AgentRole.DOCUMENTER,
AgentRole.QA,
AgentRole.MAIN_PM,
AgentRole.CELL_PM,
):
names = _tool_names(_composed_prompt_for(role, Team.BACKEND))
assert "Task" not in names, f"{role.value} must not list Task: {names}"
def test_block_is_first_layer_before_lifecycle() -> None:
"""Tools-ready block precedes the lifecycle and base layers."""
prompt = _composed_prompt_for(AgentRole.DEVELOPER, Team.BACKEND)