Configure PromptKit transient retries

This commit is contained in:
2026-09-25 21:56:29 +00:00
parent d29a5cecd3
commit 10ac29d149
19 changed files with 214 additions and 37 deletions

View File

@@ -150,10 +150,13 @@ their exit classes are defined in the [CLI reference](cli.md#output-streams-and-
Each producer binding has one outer **retries** budget. It covers complete
producer attempts for operational failures, invalid structured output,
normalizer fallback retry, and semantic correction. It is independent from
PromptKit's structural-repair calls inside one completion and from an
LLM-backed validator's own retry budget. A semantic correction rebuilds the
ordinary producer request and supplies only the latest rejected model response
plus aggregated validator guidance; it is not a conversation replay.
PromptKit's structural-repair calls inside one completion, its configured
`promptkit.transient_retries` built-in HTTP attempts, and an LLM-backed
validator's own retry budget. The transient setting defaults to two additional
attempts for eligible provider statuses; set it explicitly to zero when an
operator needs one HTTP attempt per generation. A semantic correction rebuilds
the ordinary producer request and supplies only the latest rejected model
response plus aggregated validator guidance; it is not a conversation replay.
After the applicable budgets are exhausted, the resolved
[`validation_policy`](config.md#pipelines) determines the result. Structural