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

feat(focus-area): use enriched descriptions in cluster output

Browse Source 
cluster_tasks now attaches enriched_description to each task dict.
focus-area reads enriched_description (falling back to raw content) when
building the area summary, so the orchestrator sees the expanded 3-sentence
descriptions instead of terse raw titles.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
alvis
2026-05-12 14:58:31 +00:00
parent f6b89fc849
commit f66f337779
2 changed files with 15 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ml/agents/clustering.py
View File

@@ -268,6 +268,11 @@ def cluster_tasks(
# Step 1: LLM-enrich titles → richer semantic signal before embedding. # Step 1: LLM-enrich titles → richer semantic signal before embedding.
descriptions, new_enrichments = _enrich_batch(raw_titles, persistent_cache=enrichment_cache) descriptions, new_enrichments = _enrich_batch(raw_titles, persistent_cache=enrichment_cache)
# Attach enriched description to each task dict so consumers (e.g. focus-area)
# can show the expanded text instead of the terse raw title.
for task, desc in zip(task_objs, descriptions):
task["enriched_description"] = desc
# Step 2: Prefix with nomic-embed-text task prefix, then batch-embed. # Step 2: Prefix with nomic-embed-text task prefix, then batch-embed.
prefixed = [f"clustering: {d}" for d in descriptions] prefixed = [f"clustering: {d}" for d in descriptions]
vecs = _embed_batch(prefixed) vecs = _embed_batch(prefixed)

15
ml/agents/focus_area.py
View File

@@ -45,11 +45,16 @@ class FocusAreaAgent(BaseAgent):
lines = [f"The user's tasks are grouped into {len(clusters)} area(s):"] lines = [f"The user's tasks are grouped into {len(clusters)} area(s):"]
for i, cluster in enumerate(clusters, 1): for i, cluster in enumerate(clusters, 1):
titles = [t.get("content", "").strip() for t in cluster.tasks if t.get("content")] descs = [
titles_str = "; ".join(f'"{t}"' for t in titles[:8]) t.get("enriched_description") or t.get("content", "")
if len(titles) > 8: for t in cluster.tasks
titles_str += f" (and {len(titles) - 8} more)" if t.get("content")
lines.append(f"{i}. {cluster.label} — {cluster.task_count} task(s): {titles_str}") ]
descs = [d.strip() for d in descs if d.strip()]
descs_str = "; ".join(f'"{d}"' for d in descs[:8])
if len(descs) > 8:
descs_str += f" (and {len(descs) - 8} more)"
lines.append(f"{i}. {cluster.label} — {cluster.task_count} task(s): {descs_str}")
lines.append("(Task titles may be in any language — always write the tip in English.)") lines.append("(Task titles may be in any language — always write the tip in English.)")