Your agent runs do not fail because the model is dumb. They fail because a call timed out under a budget nobody re-measured, because a weekly rate-limit window is still closed, or because a 402 was filed as "the task failed" and burned the retry budget. This pack reads your own attempt logs and answers four questions deterministically, offline, with no provider call of its own.

Who it is for

Anyone running autonomous agents in production against a coding-agent CLI or an LLM API: multi-provider workers, long-horizon runs, nightly pipelines. If you already keep a log of "which provider, which tier, how long, which exit code", this pack turns it into a routing decision.

What it answers

Question	Bucket
Is my per-tier timeout budget consistent with the calls that actually succeed?	`timeout_budgets`
Which rate-limit windows are still closed — and which only look closed?	`rate_limit_windows`
Which providers are refusing for a reason that is not a task failure?	`provider_unavailable`
Who should the next call go to, per tier?	`fallback_plan`
Which runs deserve another attempt, and from when?	`redispatch_queue`
Which failures are genuine and must not be retried?	`task_failures`
Which records are too ambiguous to judge?	`manual_review`

Quick start

sudo bash install.sh --no-service
cp examples/run_ledger.json my_runs.json
./venv/bin/python agent.py --ledger my_runs.json audit
./venv/bin/python agent.py --ledger my_runs.json report --out reliability_report.md

Each attempt needs attempt_id, run_id, tier, provider, an ISO started_at, and whatever your logs already carry: duration_s, exit_code, http_status, error_text. Anything unreadable becomes a manual_review row with the source value echoed unchanged — never a guessed number.

run attempt ledger + routing config
        |
        v
classify each attempt      (provider signal BEFORE exit code)
        |
        +--> timeout budget vs longest successful call ----+
        +--> decode rate-limit windows (weekly / session) --+
        +--> 402 / 503 / login -> provider_unavailable -----+--> fallback plan
        +--> genuine failures -> task_failures              |        |
                                                            +--> re-dispatch queue
                                                                     |
                                              JSON / Markdown report + optional BYO-LLM brief

The three mistakes it refuses to make

A provider refusal is not a task failure. 402 (membership/credit), 503 (overload) and a missing login land in provider_unavailable with task_failed: false and a soft-defer. They never consume a run's retry budget as if the work had been wrong.
A reopened window is not an outage. A rate-limit window whose reset time is at or before the audit instant is reported expired: true, blocked: false and must not keep a healthy provider out of the fallback chain. A window whose reset cannot be decoded stays blocked — the audit fails closed, never open.
A run that already succeeded, or that ended on a real assertion failure, is never re-dispatched. The first would duplicate delivered work; the second would hide a defect behind an infinite retry.

Honest operating modes

Capability	Deterministic core	Optional BYO-LLM
Attempt classification, window decoding, budget arithmetic	Yes	Not needed
Fallback plan and re-dispatch queue	Yes	Not needed
JSON and Markdown reports	Yes	Not needed
Ranked operator brief, prose refusal decoding	Template summary	Claude Code, Kimi Code, or Codex CLI

No API key and no network call are required. The optional CLI uses the subscription already connected on the machine. This agent is read-only: it never calls a provider, never edits a routing config, and never re-dispatches anything itself — config_mutated, provider_calls_made and redispatch_executed are part of every output so you can prove it.

It also does not report money. Per-run spend is a different job; this pack is about time, windows, and order.

Commands

python agent.py --ledger my_runs.json audit
python agent.py --ledger my_runs.json plan
python agent.py --ledger my_runs.json --as-of 2026-07-30T12:00:00Z audit
python agent.py --ledger my_runs.json report --out reliability_report.md
python agent.py --ledger my_runs.json brief
python agent.py status
python test_agent.py

See CUSTOMIZE.md to connect your own logs and CHECKLIST.md before you change a timeout budget from the output.

Agent LLM Run Reliability v1.0

What's inside