vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

docs/review-classifier: cost comes from OTEL labels, not the swarm UI

Browse source
This commit is contained in:
atlas 2026-10-10 19:25:09 +02:00
commit 46e9966e17
1 changed files with 14 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

31
docs/swarm/review-classifier.md
View file

@ -213,9 +213,9 @@ Two pages in the [swarm UI](ui.md), `admins` only like the rest of it.
### Recent runs
One card per run: the repo, the PR, how many classifications ran, and the
run's overall cost. Selecting a card expands it to show each
classification's result, the same rows as the review table.
One card per run: the repo, the PR, and how many classifications ran.
Selecting a card expands it to show each classification's result, the same
rows as the review table.
### Try-out
@ -231,18 +231,16 @@ that branch, where you log in as usual and open the PR yourself.
## Observability and cost
Every run records its cost, which the recent-runs page shows. Where the cost
comes from depends on the runtime:
The swarm UI shows no token counts, cache counts or cost, on any page. On the
claude runtimes, every classifier run starts its `claude` process with
`OTEL_RESOURCE_ATTRIBUTES` naming the repo and the PR, so the cost reads from
the metrics store by repo and PR. On a subscription, cost is notional.
- An ACP agent reports a running cost total (`ReportedCost` in
`hive-runtime/src/acp/stream.rs`); a session's last total is its cost.
- The `claude` CLI reports token counts, including cache reads and writes.
The dashboard already estimates a cost from token counts with a price
table (`modelPrices` in [`dashboard.md`](../web-ui/dashboard.md)).
- On a subscription, cost is notional.
The cache token counts also show whether the shared context gets the cache
reuse it's meant to.
On the ACP runtime, the harness counts the agent's `usage_update` running
totals and exports them as `hyperhive.agent.cost.usage`, labelled with only
`model` and `currency`
([`observability.md`](../scheduler/observability.md#acp-reported-cost)). That
cost has no repo or PR label yet.
The classifier logs each run's result to its journal, which ships to
VictoriaLogs like every swarm service container's
@ -280,9 +278,8 @@ These get settled, and filled in here, as the work reaches them:
account's forge token live, and which component holds the token.
- **Model naming across runtimes.** How the swarm-level model setting
handles runtime-specific model names.
- **Cost method per runtime and telemetry labels.** The exact cost source
per runtime, and the resource attributes that keep the classifier's spend
separate from the agents' on the existing dashboards.
- **ACP cost labels.** How an ACP run's cost gets a repo and PR label, so
it reads from the metrics store like the claude runtimes' cost.
- **Async message medium.** Which queue subjects or streams carry the
messages between `swarm-controller` and the classifier.
- **Reviewer handoff.** How a later reviewer, human or agent, learns the