eric/promptkit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Preserve repair settings and cumulative usage

Browse Source
This commit is contained in:
Eric Rakestraw
2026-08-11 23:21:34 +00:00
parent e43350fd0d
commit 350b0e76d9
7 changed files with 364 additions and 161 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
docs/internal/runner.md
View File

@@ -144,20 +144,27 @@ each actual generation call.
When an internal repairer is present, a JSON or JSON Schema content failure can
trigger bounded repair attempts. Repair receives the effective execution
target and session ID, validation errors, prior output, and structured-output
specification. The default repairer uses the same wrapped client as initial
generation, so each repair reacquires the selected backend's active permit
while remaining inside its original admission lease. Repair never performs a
second bounded admission, and repaired outputs use the operation's existing
validation plan. This capability remains internal and is not a public option.
target, explicit numeric-presence bits, credential, backend identity, session
ID, validation errors, prior output, and structured-output specification. One
request constructor supplies those common fields to initial and repair
generation while their rendered prompts remain intentionally distinct. The
default repairer uses the same wrapped client as initial generation, so each
repair reacquires the selected backend's active permit while remaining inside
its original admission lease. Repair never performs a second bounded
admission, and repaired outputs use the operation's existing validation plan.
This capability remains internal and is not a public option.
A successful result includes the output artifact and raw output, validation
state, effective session ID, prompt and rendered-prompt hashes, selected
profile and backend, effective settings, input hashes, token usage, a generated
run identifier, and UTC timing. The same effective session reaches initial
generation and any repair attempt through the rendered prompt. The same
effective target, including backend identity, reaches generation and any
repair attempt.
effective target and presence metadata, including backend identity and direct
credential during execution, reaches generation and every repair attempt.
Result usage is the field-wise sum of all five usage values from the initial
response and every completed repair response. Final raw output, artifact, and
validation state still come from the last candidate. A repair error returns no
partial run result or partial usage.
## Failure Categories
@@ -193,8 +200,9 @@ The [runner tests](../../internal/usecase/runner_test.go) own preparation order,
selection and override precedence, the two-phase boundary, early admission,
lease lifetime and release, direct-session resolution, schema-before-generation
behavior, hashing, generation and validation outcomes, backend propagation,
bounded repair, shared initial/repair capacity, credentials and redaction,
error categories, artifact metadata, usage, and timing. The
bounded repair progression, initial/repair request parity, cumulative usage,
shared initial/repair capacity, credentials and redaction, error categories,
artifact metadata, and timing. The
[capacity subsystem document](capacity.md) identifies the focused pool,
waiter, and wrapped-client tests.