
Show HN: Replay – Audit silent prompt cache misses in AI agent transcripts
If the agent bill went up and nothing errored, a prompt cache broke.Replay Doctor reads the transcripts already on your disk and names the turn it broke on, the cause, and the tokens re-billed at write prices. Expiry is only one of the causes it can name.$ curl -fsSL https://replay.doctor/replay.sh | lessCopyRead it, then | sh. Or go install github.com/RedRobotKK/Replay/cmd/replay@latest, or a signed release. macOS and Linux.
- ▪If the agent bill went up and nothing errored, a prompt cache broke.Replay Doctor reads the transcripts already on your disk and names the turn it broke on, the cause, and the tokens re-billed at write prices.
- ▪Expiry is only one of the causes it can name.$ curl -fsSL https://replay.doctor/replay.sh | lessCopyRead it, then | sh.
- ▪Or go install github.com/RedRobotKK/Replay/cmd/replay@latest, or a signed release. macOS and Linux.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,735 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | replay.doctor |
| Canonical URL | https://replay.doctor/ |
| Publication time | Mon, 14 Sep 2026 02:38:58 +0000 |
| Retrieval time | 2026-09-14T03:21:52.330Z |
| Last seen | 2026-09-14T03:21:52.330Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | DeQD01k04kAn · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
If the agent bill went up and nothing errored, a prompt cache broke.Replay Doctor reads the transcripts already on your disk and names the turn it broke on, the cause, and the tokens re-billed at write prices. Expiry is only one of the causes it can name.$ curl -fsSL https://replay.doctor/replay.sh | lessCopyRead it, then | sh. Or go install github.com/RedRobotKK/Replay/cmd/replay@latest, or a signed release. macOS and Linux. Nothing leaves your machine.42.9Mtokens re-read at write prices$199.77 at list, which is the price for someone billed per token. 119 sessions · 1,881 agent lanes · one machine, one operator · read 2026-09-12 by replay cost, build 0.5.4. A method demonstration, not a market.pool: 1 machine, 121 sessions, pooled 2026-09-12.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at replay.doctor.