common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(insights): hide cache read/write and cost metrics from display (#11477)

Browse Source 
The cache-read, cache-write, and total estimated-cost values shown in
/insights (and the per-model Cost column) were unreliable. Hide them from
both terminal and gateway renderings.

The underlying data pipeline is untouched — sessions still store
cache_read_tokens, cache_write_tokens, and estimated_cost_usd; the web
server, /usage command, and status bar are unaffected. Only the
InsightsEngine display layer is trimmed.

Changes:
- format_terminal: drop 'Cache read / Cache write' line, drop 'Est. cost'
  from the Total tokens row, drop per-model 'Cost' column, drop the
  '* Cost N/A for custom/self-hosted' footnote.
- format_gateway: drop cache breakdown from Tokens line, drop 'Est. cost'
  line, drop per-model cost suffix.
- Tests updated to assert these strings are now absent.
This commit is contained in:
Teknium
2026-04-17 01:02:06 -07:00
committed by GitHub
parent 3f74dafaee
commit e33cb65a98
2 changed files with 18 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
agent/insights.py
View File

@@ -634,13 +634,7 @@ class InsightsEngine:
lines.append(f" Sessions: {o['total_sessions']:<12} Messages: {o['total_messages']:,}")
lines.append(f" Tool calls: {o['total_tool_calls']:<12,} User messages: {o['user_messages']:,}")
lines.append(f" Input tokens: {o['total_input_tokens']:<12,} Output tokens: {o['total_output_tokens']:,}")
cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
if cache_total > 0:
lines.append(f" Cache read: {o['total_cache_read_tokens']:<12,} Cache write: {o['total_cache_write_tokens']:,}")
cost_str = f"${o['estimated_cost']:.2f}"
if o.get("models_without_pricing"):
cost_str += " *"
lines.append(f" Total tokens: {o['total_tokens']:<12,} Est. cost: {cost_str}")
lines.append(f" Total tokens: {o['total_tokens']:,}")
if o["total_hours"] > 0:
lines.append(f" Active time: ~{_format_duration(o['total_hours'] * 3600):<11} Avg session: ~{_format_duration(o['avg_session_duration'])}")
lines.append(f" Avg msgs/session: {o['avg_messages_per_session']:.1f}")
@@ -650,16 +644,10 @@ class InsightsEngine:
if report["models"]:
lines.append(" 🤖 Models Used")
lines.append(" " + "─" * 56)
lines.append(f" {'Model':<30} {'Sessions':>8} {'Tokens':>12} {'Cost':>8}")
lines.append(f" {'Model':<30} {'Sessions':>8} {'Tokens':>12}")
for m in report["models"]:
model_name = m["model"][:28]
if m.get("has_pricing"):
cost_cell = f"${m['cost']:>6.2f}"
else:
cost_cell = " N/A"
lines.append(f" {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,} {cost_cell}")
if o.get("models_without_pricing"):
lines.append(" * Cost N/A for custom/self-hosted models")
lines.append(f" {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,}")
lines.append("")
# Platform breakdown
@@ -739,15 +727,7 @@ class InsightsEngine:
# Overview
lines.append(f"**Sessions:** {o['total_sessions']} | **Messages:** {o['total_messages']:,} | **Tool calls:** {o['total_tool_calls']:,}")
cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
if cache_total > 0:
lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,} / cache: {cache_total:,})")
else:
lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
cost_note = ""
if o.get("models_without_pricing"):
cost_note = " _(excludes custom/self-hosted models)_"
lines.append(f"**Est. cost:** ${o['estimated_cost']:.2f}{cost_note}")
lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
if o["total_hours"] > 0:
lines.append(f"**Active time:** ~{_format_duration(o['total_hours'] * 3600)} | **Avg session:** ~{_format_duration(o['avg_session_duration'])}")
lines.append("")
@@ -756,8 +736,7 @@ class InsightsEngine:
if report["models"]:
lines.append("**🤖 Models:**")
for m in report["models"][:5]:
cost_str = f"${m['cost']:.2f}" if m.get("has_pricing") else "N/A"
lines.append(f" {m['model'][:25]} — {m['sessions']} sessions, {m['total_tokens']:,} tokens, {cost_str}")
lines.append(f" {m['model'][:25]} — {m['sessions']} sessions, {m['total_tokens']:,} tokens")
lines.append("")
# Platforms (if multi-platform)