brama tasks¶
A named task is what a caller selects as model="task:<KEY>": Brama serves it from the active route with the best recorded checks. measure sends one deterministic check to each selected route and, with --persist, records what each answered; show and list read back those records from the same journal selection reads.
brama tasks measure¶
brama tasks measure <KEY> --agent-id <ID> --prompt <TEXT> --max-models <N> [--expected-exact <TEXT>] [--expected-contains <TEXT>] [--persist] [--json] --allow-provider-cost
| Input | Required/default | Meaning |
|---|---|---|
<KEY> | required, nonempty | Key later selected as task:<KEY>. |
--agent-id <ID> | required | Agent whose subscription routes are checked. |
--prompt <TEXT> | required, nonempty | Prompt sent to every selected route. |
--expected-exact <TEXT> | one expectation required | Full score only for an exact response. |
--expected-contains <TEXT> | one expectation required | Full score when the response contains the text. |
--persist | optional; off | Record each check, so task:<KEY> selection reads it. |
--max-models <N> | required | How many active models to check; each is one billable request. No count is assumed. |
--allow-provider-cost | required by runtime; off | Acknowledge all billable requests. |
--json | optional; off | Print the report as one JSON document instead of key: value lines. |
The report holds agentId, task, persistence flag, bounds, per-model checks and the best model. Without --persist nothing is recorded.
brama tasks show¶
brama tasks show <KEY> --agent-id <ID> [--json]
Prints agent_id, task and checks: every check recorded for that task, as the journal holds it. Reads only; sends nothing to a provider.
brama tasks list¶
brama tasks list --agent-id <ID> [--json]
Prints agent_id and tasks: each task the agent has recorded checks for, with checks (how many) and newest (when the latest was taken). Reads only.
Exact refusals¶
refusing billable task-quality collection without explicit --allow-provider-cost—measurewithout the acknowledgement; exits 2 before any provider request.max_models must be at least one,task is required,prompt is required,expected_exact or expected_contains is required—measureinput refusals.no checks are recorded for task <KEY> of agent <ID>; `brama tasks measure <KEY> --agent-id <ID> --persist …` records them—showof a task nobody measured; selection refuses that task too.the journal holds a check without its task or time: <record>—listmet a malformed journal record; the record is printed whole.cannot read the journal <path>: <cause>— the journal exists but cannot be read as a file;showandlistrefuse instead of reading it as empty. Only a journal that does not exist yet is empty.the journal <path> holds a line that is not JSON (<line>): <cause>— a record the reader cannot decode; the line is printed whole and nothing after it is guessed.
Except where stated, each refusal prints to stderr and exits 1; Clap separately refuses omitted required flags before the handler runs.
See task selectors or the CLI tree.