assurance-budget

What did a coding-agent session actually do — and which limits did a run log never test?

Install

pip install assurance-budget
# or: pip install assurance   # every tool

Quick start

Session audit (Claude Code transcript — the command most people want):

$ assurance audit examples/audit/sample-session.jsonl
Claude Code session demo-8f2 — 13 min in /home/you/my-app
10 tool calls, 3 failed — Bash 6, Edit 2, Grep 1, Read 1

  Looped: 3 rounds of Bash `pytest -q tests/test_invoice.py` failing the same way, with nothing new read
  After the last edit (14:09): no test or check command ran
  Not classified: 2 shell commands, so whether they read, wrote or tested anything is unknown.
  Also in the transcript: 1 assistant turn, 1 user turn, 1 bookkeeping record.
  Not read: 0 lines.

Run-log budget (JSONL with a per-run id):

$ assurance-budget runs.jsonl
1 of 3 runs hit a limit — 1 was going nowhere first

  Limits from: built-in defaults

  r-002
      Stopped: 3 rounds repeating fetch(url=api/invoices) and failing the same way (timeout) with nothing new read and no part of the goal closer. Continuing would spend the rest of this run's budget on the same result.
  r-003
      Stopped after 20 frontier calls

  Not tested by this log: iterations, retries. The log carries no events of that kind, so this is silence rather than a pass.

As a library (stops a live loop, rather than reporting after the fact):

from assurance_core.run_budget import Budget, ProgressWatch, Progress, Spend

spend = Spend(budget=Budget.allowing(tool_calls=20))
watch = ProgressWatch()

for step in range(100):
    stopped = spend.charge_tool_call()
    if stopped:
        print(stopped.message)
        break
    stalled = watch.observe(Progress(action="fetch(url=api/invoices)", error="timeout"))
    if stalled:
        print(stalled.message)
        break

assert spend.tool_calls <= 20

What it checks

• Tool calls, failures, and loops in a Claude Code session (assurance audit)
• Edits without a prior Read or Write; whether a test or check ran after the last in-project edit
• Shell commands it could not classify (named at the same weight as findings); Not read: lines name why
• Which runs in a JSONL log hit a ceiling or stalled with nothing new read
• Which configured limits the log never exercised (silence, not a pass)

In CI

Limits

• Operator ceilings. Built-in defaults in assurance-core; raise via ~/.config/assurance/config.toml or ASSURANCE_MAX_*. Project file <cwd>/.assurance/config.toml can only lower. A caller flag can tighten, never raise past the operator.
• It reads what the log records. Unlogged spend is invisible.
• No dollar figure. Frontier calls are the cost proxy.
• Stall detection needs three identical rounds with flat progress.
• A chat transcript with no run id is refused (exit 2), not treated as one run.

See the root README and CHANGELOG.md.