Files
hermes-agent/hermes_cli/kanban_decompose.py
Teknium ff660354f3 refactor(kanban): CLI micro-helpers, action dispatch tables, shared triage helpers; active_sessions dedupe
hermes_cli/kanban.py 3,565 -> 2,912; kanban_diagnostics 1,216 -> 996;
kanban_decompose 468 -> 393; kanban_transfer 478 -> 443; kanban_specify
264 -> 229; kanban_swarm 390 -> 378; active_sessions 871 -> 775. `hermes kanban
[sub] --help` byte-identical for all 55 parsers.

- kanban.py: _err / _print_json / _json_out / _fmt_counts / _bulk_apply /
  _obj_dict field tuples replace repeated print/JSON/exit-code blocks; action
  and board subcommand routing via dict dispatch; shared run-state and
  triage-sweep argparse blocks; argparse declarations re-packed (AST-identical).
- specify/decompose: one _run_triage_sweep driver, shared _extract_json_blob /
  _truncate / _profile_author / _title_body / _resolve_profile_from_cfg.
- diagnostics: rule helpers (_first_field / _latest_event_ts / _log_hint_action
  / _error_snippet), _rows_by_task fleet fetch; unreferenced DIAGNOSTIC_KINDS dropped.
- swarm: graph nodes share one create_task kwarg set.
- active_sessions: one _flock per platform, _pid_alive via _pid_liveness,
  shared _read_live_entries / _without_lease / _clean_metadata, table-driven
  strict registry validation.
- Docstrings/comments hand-compacted (AST-identical), invariants kept.
2026-09-02 13:32:14 -07:00

394 lines
13 KiB
Python

"""Kanban decomposer — fan a triage task out into a graph of child tasks.
Invoked by ``hermes kanban decompose [task_id | --all]`` and the
auto-decompose path in the gateway dispatcher loop. Reads the user's
profile roster (with descriptions) and asks the auxiliary LLM to
return a task graph in JSON. Then atomically creates the children,
links them under the root, and flips the root ``triage -> todo``.
The root task stays alive and becomes the parent of every leaf child,
so when the whole graph completes the root wakes back up — its
assignee (the orchestrator profile) gets a chance to judge completion
and add more tasks if the work isn't done yet.
Design notes: mirrors ``kanban_specify`` (lazy aux import, lenient parse,
never raises on expected failures). The prompt sees the configured profile
roster; undescribed profiles are listed with a note so name-matching still
works. ``fanout=false`` collapses to the ``specify`` behaviour (tighten +
promote, no children), making ``decompose`` a strict superset. Unknown
assignees are rewritten to ``default_assignee`` — a child NEVER ends up with
``assignee=None``.
"""
from __future__ import annotations
import logging
import re
from dataclasses import dataclass
from typing import Optional
from hermes_cli import kanban_db as kb
from hermes_cli import profiles as profiles_mod
from hermes_cli.kanban_specify import _extract_json_blob, _title_body, _truncate
from hermes_cli.kanban_specify import _profile_author as _specify_author
logger = logging.getLogger(__name__)
_SYSTEM_PROMPT = """You are the Kanban decomposer for the Hermes Agent board.
A user dropped a rough idea into the Triage column. Your job is to break it
into a small graph of concrete child tasks and route each one to the best-
matching profile from the available roster.
You will be given:
- The original task title and body
- The list of available profiles (each with name + description)
- The fallback "default_assignee" used when no profile fits
Output a single JSON object with this exact shape:
{
"fanout": true,
"rationale": "<one sentence on why this decomposition>",
"tasks": [
{
"title": "<concrete task title, imperative voice, <= 80 chars>",
"body": "<detailed spec for the worker on this child task>",
"assignee": "<profile name from the roster, or null for default>",
"parents": [<int>, ...]
},
...
]
}
Rules:
- "parents" is a list of INDICES (0-based) into this same "tasks" list,
expressing actual data dependencies. Tasks with no parents run in
PARALLEL. Tasks with parents wait until every parent completes.
- Prefer parallelism. If two tasks can be done independently, give
them no parents so the dispatcher fans them out at once.
- Use 2-6 tasks for normal work. Don't create 20 tiny tasks. Don't
cram everything into 1 task.
- Pick assignees from the roster by matching the task to the profile's
DESCRIPTION (not just the name). When nothing matches well, use null
and the system will route to the default_assignee.
- Each child task body is what a fresh worker will read with no other
context — be specific about goal, approach, and acceptance criteria.
When the task is genuinely a single unit of work (no useful decomposition),
return:
{
"fanout": false,
"rationale": "<one sentence>",
"title": "<tightened title>",
"body": "<concrete spec for a single worker>",
"assignee": "<profile name from the roster, or null for default>"
}
In that case the task stays as one work item, just with a tightened spec and
a concrete assignee. If no profile fits, use null and the system will route to
the default_assignee.
No preamble, no closing remarks, no code fences. Output only the JSON object.
"""
_USER_TEMPLATE = """Task id: {task_id}
Title: {title}
Body:
{body}
Available profiles (assignees you may pick from):
{roster}
Default assignee (used when no profile fits a task): {default_assignee}
"""
_FENCE_RE = re.compile(r"^```(?:json)?\s*|\s*```$", re.MULTILINE)
@dataclass
class DecomposeOutcome:
"""Result of decomposing a single triage task."""
task_id: str
ok: bool
reason: str = ""
fanout: bool = False
child_ids: list[str] | None = None
new_title: Optional[str] = None
def _profile_author() -> str:
"""Mirror of ``hermes_cli.kanban._profile_author``."""
return _specify_author("decomposer")
def _load_config() -> dict:
try:
from hermes_cli.config import load_config
return load_config() or {}
except Exception:
return {}
def _resolve_profile_from_cfg(cfg: dict, key: str) -> str:
"""``kanban.<key>`` if it names an existing profile, else the active
default profile — so a task is never stranded for lack of an owner.
``orchestrator_profile`` owns the root after fan-out; ``default_assignee``
catches children the decomposer can't route.
"""
kanban_cfg = cfg.get("kanban", {}) if isinstance(cfg, dict) else {}
explicit = (kanban_cfg.get(key) or "").strip()
if explicit:
try:
if profiles_mod.profile_exists(explicit):
return explicit
except Exception:
pass
try:
return profiles_mod.get_active_profile_name() or "default"
except Exception:
return "default"
def _build_roster() -> tuple[list[dict], set[str]]:
"""``(roster_for_prompt, valid_assignee_names)``; entries are
``{name, description, has_description}``."""
roster: list[dict] = []
valid: set[str] = set()
try:
all_profiles = profiles_mod.list_profiles()
except Exception as exc:
logger.warning("decompose: failed to list profiles: %s", exc)
return roster, valid
for p in all_profiles:
desc = (p.description or "").strip()
roster.append({
"name": p.name,
"description": desc or f"(no description; profile named {p.name!r})",
"has_description": bool(desc),
})
valid.add(p.name)
return roster, valid
def _format_roster(roster: list[dict]) -> str:
if not roster:
return " (no profiles installed — decomposer cannot route work)"
lines = []
for entry in roster:
tag = "" if entry["has_description"] else " ⚠ undescribed"
lines.append(f" - {entry['name']}{tag}: {entry['description']}")
return "\n".join(lines)
def _normalize_assignee_choice(
assignee: object,
*,
default_assignee: str,
valid_names: set[str],
) -> str:
"""A valid assignee, else ``default_assignee`` — promoted work is never
left unassigned."""
if not isinstance(assignee, str) or not assignee.strip():
return default_assignee
chosen = assignee.strip()
if chosen not in valid_names:
return default_assignee
return chosen
def decompose_task(
task_id: str,
*,
author: Optional[str] = None,
timeout: Optional[int] = None,
) -> DecomposeOutcome:
"""Decompose a triage task into a graph of child tasks. Expected failures
(not in triage, no aux client, API error, malformed/empty reply) surface
as ``ok=False``."""
with kb.connect_closing() as conn:
task = kb.get_task(conn, task_id)
if task is None:
return DecomposeOutcome(task_id, False, "unknown task id")
if task.status != "triage":
return DecomposeOutcome(
task_id, False, f"task is not in triage (status={task.status!r})"
)
cfg = _load_config()
orchestrator = _resolve_profile_from_cfg(cfg, "orchestrator_profile")
default_assignee = _resolve_profile_from_cfg(cfg, "default_assignee")
kanban_cfg = cfg.get("kanban", {}) if isinstance(cfg, dict) else {}
auto_promote = bool(kanban_cfg.get("auto_promote_children", True))
roster, valid_names = _build_roster()
try:
from agent.auxiliary_client import call_llm # type: ignore
except Exception as exc:
logger.debug("decompose: auxiliary client import failed: %s", exc)
return DecomposeOutcome(task_id, False, "auxiliary client unavailable")
user_msg = _USER_TEMPLATE.format(
task_id=task.id,
title=_truncate(task.title or "", 400),
body=_truncate(task.body or "(no body)", 4000),
roster=_format_roster(roster),
default_assignee=default_assignee,
)
try:
# call_llm applies all auxiliary.kanban_decomposer.* config
# (provider/model/base_url, extra_body, reasoning_effort, retries).
resp = call_llm(
task="kanban_decomposer",
messages=[
{"role": "system", "content": _SYSTEM_PROMPT},
{"role": "user", "content": user_msg},
],
temperature=0.3,
max_tokens=4000,
timeout=timeout or 180,
)
except Exception as exc:
logger.info(
"decompose: API call failed for %s (%s)", task_id, exc,
)
return DecomposeOutcome(task_id, False, f"LLM error: {type(exc).__name__}")
try:
raw = resp.choices[0].message.content or ""
except Exception:
raw = ""
parsed = _extract_json_blob(raw, _FENCE_RE)
if parsed is None:
return DecomposeOutcome(task_id, False, "LLM returned malformed JSON")
fanout = bool(parsed.get("fanout"))
audit_author = author or _profile_author()
if not fanout:
# Fall back to single-task spec promotion (same effect as specify).
title_val, body_val = _title_body(parsed)
assignee_val = None
if not task.assignee:
assignee_val = _normalize_assignee_choice(
parsed.get("assignee"),
default_assignee=default_assignee,
valid_names=valid_names,
)
if title_val is None and body_val is None:
return DecomposeOutcome(
task_id, False, "decomposer returned fanout=false with no title/body",
)
with kb.connect_closing() as conn:
ok = kb.specify_triage_task(
conn,
task_id,
title=title_val,
body=body_val,
assignee=assignee_val,
author=audit_author,
)
if not ok:
return DecomposeOutcome(
task_id, False, "task moved out of triage before promotion",
)
return DecomposeOutcome(
task_id, True, "single task (no fanout)",
fanout=False, new_title=title_val,
)
raw_tasks = parsed.get("tasks") or []
if not isinstance(raw_tasks, list) or not raw_tasks:
return DecomposeOutcome(
task_id, False, "decomposer returned fanout=true with empty tasks list",
)
# Unknown assignees route to the default; never assignee=None.
children: list[dict] = []
for idx, entry in enumerate(raw_tasks):
if not isinstance(entry, dict):
return DecomposeOutcome(
task_id, False, f"tasks[{idx}] is not an object",
)
title = entry.get("title")
if not isinstance(title, str) or not title.strip():
return DecomposeOutcome(
task_id, False, f"tasks[{idx}].title is missing or empty",
)
body = entry.get("body")
if not isinstance(body, str):
body = ""
assignee = entry.get("assignee")
chosen = _normalize_assignee_choice(
assignee,
default_assignee=default_assignee,
valid_names=valid_names,
)
if (
isinstance(assignee, str)
and assignee.strip()
and assignee.strip() not in valid_names
):
logger.info(
"decompose: task %s child %d picked unknown assignee %r — "
"routing to default_assignee %r",
task_id, idx, assignee, default_assignee,
)
parents = entry.get("parents") or []
if not isinstance(parents, list):
parents = []
# Clean parent indices: drop non-int and out-of-range.
clean_parents = [p for p in parents if isinstance(p, int) and 0 <= p < len(raw_tasks) and p != idx]
children.append({
"title": title.strip()[:200],
"body": body.strip(),
"assignee": chosen,
"parents": clean_parents,
})
try:
with kb.connect_closing() as conn:
child_ids = kb.decompose_triage_task(
conn,
task_id,
root_assignee=orchestrator,
children=children,
author=audit_author,
auto_promote=auto_promote,
)
except ValueError as exc:
return DecomposeOutcome(task_id, False, f"DB rejected graph: {exc}")
except Exception as exc:
logger.exception("decompose: DB error on task %s", task_id)
return DecomposeOutcome(task_id, False, f"DB error: {type(exc).__name__}")
if child_ids is None:
return DecomposeOutcome(
task_id, False, "task moved out of triage before decomposition",
)
return DecomposeOutcome(
task_id, True, f"decomposed into {len(child_ids)} children",
fanout=True, child_ids=child_ids,
)
def list_triage_ids(*, tenant: Optional[str] = None) -> list[str]:
"""Return task ids currently in the triage column."""
with kb.connect_closing() as conn:
rows = kb.list_tasks(
conn,
status="triage",
tenant=tenant,
limit=1000,
)
return [row.id for row in rows]