Configure PromptKit transient retries

docs/config.md

@@ -102,6 +102,7 @@ version: 5
 promptkit:
   profile_dir: ./profiles
   # profile_file: ./profiles.yml
+  transient_retries: 2
   local_backend:
     endpoint: http://localhost:8000/v1
     concurrency_limit: 2
@@ -111,6 +112,7 @@ promptkit:
 | --- | --- | --- |
 | **profile_dir** | string | Non-empty directory containing profile files. |
 | **profile_file** | string | Non-empty profile file. |
+| **transient_retries** | integer | Non-negative additional built-in HTTP attempts for eligible transient provider failures; defaults to 2. Set 0 to disable these retries. |
 | **local_backend** | object | Optional registration for the conventional PromptKit backend ID **local**. |
 | **local_backend.endpoint** | string | Required when **local_backend** is present; absolute HTTP or HTTPS URL with a host. |
 | **local_backend.concurrency_limit** | integer | Optional non-negative limit; defaults to 0. |

docs/internal/configuration.md

@@ -44,7 +44,9 @@ concurrency settings, malformed bindings and references, invalid retries, and
 invalid pipeline, step, or lane structure. PromptKit local-backend validation
 accepts only an absolute HTTP or HTTPS endpoint with a host and no user
 information, query, or fragment, and rejects a negative local concurrency
-limit. Its errors retain the closest known pipeline, lane, and binding context.
+limit. It also rejects a negative `promptkit.transient_retries` value; decoded
+omission resolves to two, while explicit zero remains a distinct opt-out. Its
+errors retain the closest known pipeline, lane, and binding context.
 It deliberately does not require modules to be registered: that requires a
 catalog and belongs to resolution.
 
@@ -119,6 +121,8 @@ recording arbitrary environment values or provider requests.
 - Whitespace-normalized identifiers are unique wherever they identify a
   pipeline, step, lane, worker, or reference slot.
 - Runtime conversion and resolved-pipeline publication return detached data.
+- The resolved PromptKit transient-retry budget is always passed to the shared
+  built-in client; document presence preserves an explicit zero.
 - The resolved digest changes when resolved composition changes and never
   includes itself.
 

docs/internal/llm.md

@@ -264,10 +264,12 @@ deadline. The HTTP client timeout is a separate transport-wide cap. Notarius
 forwards the caller context and does not install another timeout wrapper around
 PromptKit.
 
-The selected PromptKit profile owns generation settings. PromptKit v0.11.0
-performs up to two additional built-in attempts for eligible transient HTTP
-failures in one generation, while Notarius binding retries remain outside the
-adapter and repeat the complete module operation and validation chain.
+The selected PromptKit profile owns generation settings. The resolved global
+`promptkit.transient_retries` configuration is passed to the shared PromptKit
+engine and controls additional built-in attempts for eligible transient HTTP
+failures in one generation. It defaults to two; explicit zero disables those
+attempts. Notarius binding retries remain outside the adapter and repeat the
+complete module operation and validation chain.
 Operator-facing behavior is summarized in
 [Operations](../operations.md#operational-limits), and the pinned upstream
 contract is identified in

docs/operations.md

@@ -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

docs/roadmap/implementation.md

@@ -133,6 +133,8 @@ dependency's default retry behavior and license accurately.
 
 ## Stage 3 — Wire The Explicit Transient Retry Setting
 
+**Status:** Completed 2026-09-25.
+
 **Goal:** Make retry policy inspectable and configurable through the one shared
 engine. One prompt covering a single vertical configuration slice.