Accumulate usage metrics across tool call iterations

[Copilot]

When using tools with track_usage=True, only the final API call's usage was tracked, underreporting token consumption and costs across multi-turn tool loops.

Changes

• Modified _run_tool_loop: Returns all API responses from every iteration, not just the final response
• Added _accumulate_usage_metrics: Sums token counts (input, output, cached) across all API responses in tool loops
• Updated query_unified: Uses accumulated metrics when tools are present, single-call metrics otherwise

Example

# Previously: only final API call tracked
result = agent.query_unified(
    message="Get data and analyze it",
    tools=[get_data_tool, analyze_tool],
    track_usage=True
)
# result.usage.input_tokens would undercount by missing tool iteration tokens

# Now: cumulative tracking across all calls
result = agent.query_unified(
    message="Get data and analyze it", 
    tools=[get_data_tool, analyze_tool],
    track_usage=True
)
# result.usage.input_tokens = sum of all iterations (e.g., 100 + 150 = 250)
# result.usage.output_tokens = sum of all iterations (e.g., 20 + 30 = 50)

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[Copilot]

Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• astral.sh
  • Triggering command: /usr/bin/curl curl -LsSf REDACTED (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)