Renewal summary for the Wi-Fi services contract
The request
The task request supplied to the adapter, alongside the workspace below. Runtime instructions, authorized tools and skills also affect the system. Containerized runs withhold host-side references; local mode is not an isolation boundary.
Timothy wants a renewal summary of our Brightline Wi-Fi contract before we decide whether to go out to bid; the note in the folder says what is needed. Save it as renewal_summary.md.
Workspace
- contracts/Amendment_1_Driftwood_Cottages.pdf
- contracts/Amendment_2_signed.pdf
- contracts/Amendment_3_DRAFT_for_discussion.pdf
- contracts/Brightline_MSA_Saltmarsh_executed.pdf
- contracts/Go-Live_Certificate.pdf
- email_from_brightline.txt
- note_from_owner.txt
Expected deliverables
- renewal_summary.md
This task also has a task-specific grader (check.py).
Recorded acceptance checks
The table uses check names and outcomes from the frozen campaign ledger. Acceptance requires all required predicates to pass; a predicate may itself contain a tolerance or coverage threshold. Its scope is part of the measurement contract.
| Recorded check | Type | Required | Failed / observed |
|---|---|---|---|
| renewal_summary.md exists | file_exists | yes | 0 / 6 |
| current annual value | text_numbers_present | yes | 0 / 6 |
| term, notice and the vendor's figures | custom | yes | 1 / 6 |
| automatic renewal | text_sentence_matches | yes | 0 / 6 |
| renewal price cap | text_sentence_matches | yes | 0 / 6 |
Current task declaration (5 checks)
From task.yaml. Original runner grading and frozen retrospective scoring are separate. Read the frozen source for the rules behind the reported results.
- renewal_summary.md exists —
file_exists, required - current annual value —
text_numbers_present, required - term, notice and the vendor's figures —
custom, required - automatic renewal —
text_sentence_matches, required - renewal price cap —
text_sentence_matches, required
Recorded results, desk release
| System | Repetitions | Frozen / 3 | Original / 3 | Median minutes | Mean model estimate (USD) |
|---|---|---|---|---|---|
| Proto / DeepSeek V4.1 Flash | 2 | 1 | 0.8 | 0.0114 | |
| Codex / GPT-5.6 sol | 3 | 3 | 1.5 | 0.1406 |
These are repeated executions on the released fixture, not independent new business cases. Cost is captured model usage priced under the recorded assumptions, excluding infrastructure and human review. Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "contract-renewal-summary".
Recorded results, desk comparison, 28 September 2026
| System | Repetitions | Frozen / 3 | Original / 3 | Median minutes |
|---|---|---|---|---|
| Proto / GPT-6 sol | 3 | 3 | 1.2 | |
| Codex / GPT-6 sol | 1 | 1 | 0.9 | |
| Proto / DeepSeek V4.1 Flash | 3 | 0 | 0.8 |
A separate campaign under the same frozen scorer, not pooled with the release. Conditions and data.