Skip to content

📊 Copilot Token Usage Report2026-04-05 #1676

@github-actions

Description

@github-actions

Overview

Period: 2026-04-04T10:20Z to 2026-04-05T10:20Z
Runs analyzed: 30 total (1 had token data)
Total tokens: 1,399K
Estimated total cost: $2.02 (Copilot rates: $2.50/M input, $10/M output)

🆕 New workflow with token data: Pelis Agent Factory Advisor appears for the first time with token data — 11 requests, $2.02 per run.

ℹ️ Secret Digger (Copilot) absent: Only Claude and Codex variants of Secret Digger ran today. The Copilot variant did not run in this period (not a failure — it simply wasn't scheduled or triggered).

Workflow Summary

Workflow Runs Requests Total Tokens Est. Cost Cache Rate I/O Ratio Top Model
Pelis Agent Factory Advisor 1 11 1,399K $2.02 45.2% 110:1 claude-sonnet-4.6
Total 1 11 1,399K $2.02 45.2% 110:1

🔍 Optimization Opportunities

  1. Pelis Agent Factory Advisor — low cache hit rate (45.2% < 50%)

    • First request always cold (0 cache reads, 39,950 input tokens) — full system prompt cost each run
    • Cache warms progressively from request 2 onwards (reaching ~49% by req 6–11)
    • Recommendation: Ensure the system prompt prefix is stable across requests so Anthropic's prompt cache can pre-warm it; consider structuring the first request to maximize the cacheable prefix
  2. Pelis Agent Factory Advisor — high I/O ratio (110:1 > 100:1 threshold)

    • 759K input tokens vs only 13K output tokens across 11 requests
    • Input context grows from 40K → 83K over 11 turns (conversation history accumulation)
    • Recommendation: Review whether all prior conversation history needs to be included each turn; consider summarizing or truncating older turns
  3. No cache_write tokens (Copilot provider limitation)

    • cache_write_tokens is 0 across all requests — the Copilot inference endpoint does not report this separately
    • Cost estimates may be slightly understated (cache write overhead not billed separately here)
    • Status: Known limitation, no action needed
Per-Workflow Details

Pelis Agent Factory Advisor

  • Run: §23993514169 (run feat: make allow-domains optional (blocks all traffic when not specified) #80, success, triggered by schedule, actor: dsyme)
  • Requests: 11 total
  • Model: claude-sonnet-4.6 via Copilot endpoint
  • AWF version: v0.20.1
  • Session duration: 03:39:29 → 03:43:18 UTC (~4 minutes)
  • Tokens: 1,399K total (759K input, 13K output, 627K cache_read, 0 cache_write)
  • Cache hit rate: 45.2% (cold start on req 1, warming progressively)
  • I/O ratio: 110:1
  • Avg latency: 20,490ms/request (median ~8,000ms; req 10 took 88,691ms for a 5K-token response)
  • Estimated cost: $2.02

Per-request breakdown:

Req Input Output Cache Read Cache Rate Latency Cost
1 39,950 400 0 0% 7,045ms $0.10
2 59,297 520 33,976 36% 8,090ms $0.15
3 61,343 505 46,636 43% 7,688ms $0.16
4 69,222 513 53,989 44% 8,043ms $0.18
5 71,086 497 61,605 46% 7,772ms $0.18
6 68,647 362 66,345 49% 6,177ms $0.18
7 73,335 443 67,410 48% 14,526ms $0.19
8 76,012 1,794 70,372 48% 33,149ms $0.21
9 78,685 2,227 73,051 48% 35,288ms $0.22
10 78,289 4,959 75,657 49% 88,691ms $0.25
11 83,324 348 78,288 48% 8,920ms $0.21

Observation: Input context grows monotonically (39K → 83K), consistent with conversation history accumulation. Requests 8–10 show significantly higher output tokens (1,794 / 2,227 / 4,959) and latency, suggesting heavier model work in later turns. Request 10 took 88.7 seconds for a 4,959-token response.

Workflows Without Token Data

The following Copilot-engine workflows ran but produced no agent-artifacts with token-usage.jsonl:

Workflow Runs Conclusion Reason
Secret Digger (Copilot) 0 Did not run this period (only Claude/Codex variants ran)
Smoke Services 1 ❌ failure Has artifacts (agent, detection, firewall-audit-logs) but no agent-artifacts — likely failed before AWF agent completed
Plan Command 2 ⏭️ skipped Skipped — condition not met
Agentic Maintenance 5 ✅ success No artifacts — does not use --enable-api-proxy
Firewall Issue Dispatcher 2 ✅ success Has agent artifact but not agent-artifacts — does not use --enable-api-proxy

Excluded from scope (Claude/Codex engine): Secret Digger (Claude) (6 runs), Secret Digger (Codex) (6 runs), Smoke Claude (1 run), Smoke Codex (1 run)

Historical Trend

Period Workflow Runs Total Tokens Est. Cost Cache Rate Notes
2026-04-05 Pelis Agent Factory Advisor 1 1,399K $2.02 45.2% First appearance
2026-04-04 Secret Digger (Copilot) 4 752K $1.16 33.6% 1 failure (retry loop)
2026-04-03 Secret Digger (Copilot) 5 850K $1.33 38.1% 1 failure (retry loop)
2026-04-03 Documentation Maintainer 1 3,003K $3.91 48.7% Only appeared once
2026-04-03 Total 6 3,853K $5.24 46.0%

Trend observations:

  • Secret Digger (Copilot) absent today — daily cost down from $1.16 to $2.02 net, but driven by new Pelis workflow rather than efficiency gains
  • Pelis Agent Factory Advisor ($2.02/run) is more expensive per run than Secret Digger success runs ($0.18/run), reflecting its longer agentic session (11 vs 2 requests, 4 minutes of work)
  • Documentation Maintainer ($3.91/run) has not re-appeared since 2026-04-03 — most expensive workflow seen so far
  • The recurring retry-loop bug in Secret Digger (Copilot) cannot be assessed today (no Copilot variant runs)

Previous Report

📊 Copilot Token Usage Report 2026-04-04

References:

Generated by Daily Copilot Token Usage Analyzer ·

Metadata

Metadata

Assignees

No one assigned

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions