fix(tests): drop the ignored observer from the config_summary fixtures
`observer_peer_id` has no effect on a `get_context` step — the runner does not forward it — so it read as scoping a request that was never scoped. The step description now records that these are unscoped reads and what naming an observer would change. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
bd410c7840
commit
65cb42186c
|
|
@ -85,7 +85,7 @@
|
|||
"session_id": "session_summary",
|
||||
"summary": true,
|
||||
"max_tokens": 4000,
|
||||
"observer_peer_id": "eve",
|
||||
"description": "Unscoped read, so the summary gets 40% of max_tokens. Naming an observer would route through the peer_target path, where the representation and peer card are subtracted from the budget first.",
|
||||
"assertions": [
|
||||
{
|
||||
"assertion_type": "llm_judge",
|
||||
|
|
|
|||
|
|
@ -84,7 +84,7 @@
|
|||
"session_id": "session_summary",
|
||||
"summary": true,
|
||||
"max_tokens": 4000,
|
||||
"observer_peer_id": "eve",
|
||||
"description": "Unscoped read, so the summary gets 40% of max_tokens. Naming an observer would route through the peer_target path, where the representation and peer card are subtracted from the budget first.",
|
||||
"assertions": [
|
||||
{
|
||||
"assertion_type": "llm_judge",
|
||||
|
|
|
|||
Loading…
Reference in New Issue