alvis/oO
1
0
Fork 0
Code Issues 34 Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(focus-area): output all clusters as context; remove scoring and preferred_areas

Browse Source 
The agent no longer picks a winner — it summarises every cluster so the
orchestrator can decide what's relevant. Scoring by overdue count overlapped
with the overdue-task agent. preferred_areas (project-ID based, broken label
matching) removed entirely.

Output format: numbered list of areas with task titles included.
Snapshot: {cluster_count, clusters: [{label, task_count, tasks}]}.
Version bumped to 3.0.0; inferred_params cleared.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
alvis
2026-05-12 14:57:04 +00:00
parent 12c956b588
commit f6b89fc849
3 changed files with 69 additions and 168 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
ml/agents/focus_area.py
View File

@@ -1,69 +1,37 @@
from __future__ import annotations
from collections import Counter
from typing import ClassVar
from .base import BaseAgent, AgentInput, AgentOutput
from .clustering import cluster_tasks
from .inference.history import UserHistory
from .manifest import AgentManifest, InferredParam
def _infer_preferred_areas(history: UserHistory) -> list[str]:
"""Top-2 project IDs by completed task count (last 90 days worth of data)."""
counts: Counter[str] = Counter()
for tc in history.task_completions:
if tc.project_id:
counts[tc.project_id] += 1
return [pid for pid, _ in counts.most_common(2)]
from .manifest import AgentManifest
MANIFEST = AgentManifest(
id="focus-area",
version="2.1.0", # 1h TTL + task-change detection (#129)
description="Identifies the most congested semantic focus area in the user's task list.",
pref_schema={
"type": "object",
"additionalProperties": False,
"properties": {
"preferred_areas": {
"type": "array",
"items": {"type": "string"},
"default": [],
"description": "Project IDs or label names to prioritise when multiple areas tie.",
},
},
},
version="3.0.0", # output all clusters as context; no scoring (#129)
description="Clusters the user's task list and summarises all areas for the orchestrator.",
pref_schema={"type": "object", "additionalProperties": False, "properties": {}},
context_schema=["todoist.tasks"],
required_consents=["data:core", "data:todoist"],
output_contract={"type": "snippet", "format": "free_text"},
ttl_sec=86_400,
inferred_params=[
InferredParam(
key="preferred_areas",
ttl_sec=86_400,
cold_start_default=[],
min_history=0, # use task_completions, not feedback events; handle empty inside
infer=_infer_preferred_areas,
),
],
inferred_params=[],
)
class FocusAreaAgent(BaseAgent):
"""Identifies the most congested semantic focus area in the user's task list."""
"""Clusters tasks and outputs a full area summary for the orchestrator."""
agent_id: ClassVar[str] = MANIFEST.id
ttl_seconds: ClassVar[int] = MANIFEST.ttl_sec
version: ClassVar[str] = MANIFEST.version # 2.1.0
version: ClassVar[str] = MANIFEST.version # 3.0.0
def compute(self, inp: AgentInput) -> AgentOutput:
preferred: list[str] = inp.agent_prefs.get("preferred_areas", [])
if not inp.tasks:
return self._make_output(
inp,
"No tasks available to identify a focus area.",
{"cluster_count": 0, "strategy": "none"},
"No tasks available to identify focus areas.",
{"cluster_count": 0},
)
clusters, new_enrichments = cluster_tasks(inp.tasks, enrichment_cache=inp.enrichment_cache)
@@ -71,45 +39,27 @@ class FocusAreaAgent(BaseAgent):
if not clusters:
return self._make_output(
inp,
"No tasks available to identify a focus area.",
{"cluster_count": 0, "strategy": "none"},
"No tasks available to identify focus areas.",
{"cluster_count": 0},
)
strategy = "semantic" if len(clusters) > 1 or len(inp.tasks) > 1 else "fallback"
lines = [f"The user's tasks are grouped into {len(clusters)} area(s):"]
for i, cluster in enumerate(clusters, 1):
titles = [t.get("content", "").strip() for t in cluster.tasks if t.get("content")]
titles_str = "; ".join(f'"{t}"' for t in titles[:8])
if len(titles) > 8:
titles_str += f" (and {len(titles) - 8} more)"
lines.append(f"{i}. {cluster.label} — {cluster.task_count} task(s): {titles_str}")
def score(cluster) -> float:
base = sum(2.0 if t.get("is_overdue") else 1.0 for t in cluster.tasks)
boosted = any(p in cluster.label for p in preferred) if preferred else False
return base + (0.5 if boosted else 0.0)
top = max(clusters, key=score)
boosted = bool(preferred) and any(p in top.label for p in preferred)
parts = [
f'The user\'s most active focus area is "{top.label}" '
f"({top.task_count} task{'s' if top.task_count != 1 else ''}, "
f"{top.overdue_count} overdue). "
f"(Note: task titles may be in any language — always write the tip in English.)"
]
if boosted:
parts.append("This area matches the user's stated focus preferences.")
if top.overdue_count >= 3:
parts.append("Consider surfacing an action from this area.")
if len(clusters) > 1:
other_total = sum(c.task_count for c in clusters if c is not top)
parts.append(
f"{len(clusters) - 1} other area{'s' if len(clusters) > 2 else ''} "
f"contain {other_total} task{'s' if other_total != 1 else ''}."
)
lines.append("(Task titles may be in any language — always write the tip in English.)")
snapshot = {
"top_cluster_label": top.label,
"top_task_count": top.task_count,
"top_overdue_count": top.overdue_count,
"cluster_count": len(clusters),
"strategy": strategy,
"preferred_areas": preferred,
# Consumed by compute_agent endpoint; stripped before storing the snapshot.
"clusters": [
{"label": c.label, "task_count": c.task_count,
"tasks": [t.get("content", "") for t in c.tasks]}
for c in clusters
],
"_new_enrichments": new_enrichments,
}
return self._make_output(inp, " ".join(parts), snapshot)
return self._make_output(inp, "\n".join(lines), snapshot)