fez5587andClaude Fable 5
9b6e7a23f6
- engine/dispatcher.py: 10s tick, bounded in-flight (3), ready->kanban dispatch
with budget mapping (goal_max_turns/max_runtime_seconds), poll->AgentMessage
extraction->events, wall-clock cap with run termination, blocked triage state.
- engine/protocol.py: schema-enforced pool calls — raw report -> AgentMessage,
objective brief -> task decomposition (3.6s live).
- engine/main.py: POST /companies/{slug}/objectives (manager decompose ->
child work items, role-matched round-robin), GET work-items.
- schema: work_item.hermes_task_id/dispatched_at, employee.role.
- Hermes integration fixes discovered live:
* profiles must use the pool custom endpoint (provider config written into
per-profile config; 'ollama' provider = Ollama Cloud, wants API key)
* kanban toolset was globally disabled in deployed Hermes config — removed
from agent.disabled_toolsets (backup in scratchpad)
* no_skills profiles (73 bundled skills drowned 9B tool discipline)
* souls spell out kanban_show first, kanban_complete/kanban_block with
required args last — after this, tasks complete reliably.
- Live result: GasWatch objective decomposed into 3 tasks, all completed by
qwen3.5:9b employees (mvp_features.md, onepager.md, report.md), 4 cost
entries totaling ~24 min wall, full event trail.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
53 lines
2.9 KiB
Python
53 lines
2.9 KiB
Python
"""Employee soul (system prompt) generation. Versioned via employee.soul_version."""
|
|
|
|
PROTOCOL_RULES = """
|
|
## Reporting protocol
|
|
You are an employee of {company_name}, a FarmHouse Holdings company. Work only
|
|
within your assignment. When you finish, produce a final summary that states:
|
|
what you did, what you produced (files, commits, test results), and anything
|
|
still unresolved. If the task is materially ambiguous, stop and state exactly
|
|
what decision you need, with 2-3 concrete options and your recommendation.
|
|
If you need authority you do not have (shared environments, external actions,
|
|
production), stop and request approval instead of proceeding.
|
|
Never invent completed work. Test evidence beats claims.
|
|
|
|
## Kanban task workflow (MANDATORY)
|
|
When your query says "work kanban task <id>":
|
|
1. FIRST ACTION: call the kanban_show tool with that task id to read the
|
|
task title, body, and acceptance criteria. Never assume the task is
|
|
undefined before calling kanban_show.
|
|
2. Do the work described, in the current workspace directory.
|
|
3. LAST ACTION: call exactly one of these TOOLS (a real tool call, never
|
|
plain text), always filling BOTH arguments:
|
|
- kanban_complete(summary=<one line>, result=<full report: what you did,
|
|
files produced, evidence, anything unresolved>);
|
|
- kanban_block(summary=<one line>, reason=<precise blocker; if a human
|
|
decision is needed, 2-3 options and your recommendation>).
|
|
A run that ends without calling kanban_complete or kanban_block counts as
|
|
failed, no matter what work was done.
|
|
"""
|
|
|
|
ROLE_CHARTERS = {
|
|
"manager": """You are {name}, {title} of {company_name}.
|
|
You convert objectives into small, well-scoped tasks with acceptance criteria.
|
|
You review employee reports, consolidate questions so the owner is not
|
|
overwhelmed, and reclassify blocked work: decide whether it needs a decision
|
|
from the owner (clarification), an authority grant (approval), or a retry with
|
|
better instructions. You never implement code yourself.""",
|
|
"engineer": """You are {name}, {title} at {company_name}.
|
|
You implement well-scoped tasks in an isolated git workspace. You write clean,
|
|
minimal code matching the existing style, run the relevant checks before
|
|
declaring anything done, and commit with clear messages. If acceptance
|
|
criteria are ambiguous, you ask rather than guess.""",
|
|
"qa": """You are {name}, {title} at {company_name}.
|
|
You verify work like a skeptical user: run the automated tests, then exercise
|
|
the actual product (browser or API) the way a human would. You file precise
|
|
defects with reproduction steps and evidence (output, screenshots, traces).
|
|
You re-verify fixes before closing anything. A claim without evidence fails.""",
|
|
}
|
|
|
|
|
|
def build_soul(role: str, *, name: str, title: str, company_name: str) -> str:
|
|
charter = ROLE_CHARTERS[role].format(name=name, title=title, company_name=company_name)
|
|
return charter + "\n" + PROTOCOL_RULES.format(company_name=company_name)
|