Prepare documentation for the v0.8.0 release

README.md

@@ -33,10 +33,16 @@ boundary and constraints that framework work must preserve.
 
 ## Release Guidance
 
-Consumers upgrading from `v0.5.0` to `v0.6.0` should read the
+Consumers upgrading from `v0.7.0` to `v0.8.0` should read the
-[v0.6.0 changelog and migration guide](docs/releases/v0.6.0.md).
+[v0.8.0 changelog and migration guide](docs/releases/v0.8.0.md).
 
 Earlier adopters can consult the
+[v0.7.0 changelog and migration guide](docs/releases/v0.7.0.md).
+
+Consumers upgrading from `v0.5.0` to `v0.6.0` can consult the
+[v0.6.0 changelog and migration guide](docs/releases/v0.6.0.md).
+
+Consumers upgrading from `v0.4.0` to `v0.5.0` can consult the
 [v0.5.0 changelog and migration guide](docs/releases/v0.5.0.md).
 
 Consumers upgrading from `v0.3.0` to `v0.4.0` should read the

backends.go

@@ -30,9 +30,12 @@ type Backend struct {
 	// requires an absolute HTTP or HTTPS URL with a host and without user
 	// information, a query string, or a fragment. Paths are allowed.
 	Endpoint string
-	// APIKeyEnv optionally names the environment variable containing the API
+	// APIKeyEnv optionally names an environment lookup source for an API key.
-	// key. NewEngine trims it and requires the portable form
+	// NewEngine trims it and requires the portable form [A-Za-z_][A-Za-z0-9_]*.
-	// [A-Za-z_][A-Za-z0-9_]*. Store only the name, never a credential value.
+	// A direct RunRequest.APIKey takes precedence. When no usable credential is
+	// available, the built-in client omits Authorization; injected clients own
+	// their own credential-resolution behavior. Store only the name, never a
+	// credential value.
 	APIKeyEnv string
 	// ExtraParams contains backend-wide request defaults. Values must be
 	// JSON-compatible, finite, acyclic, and keyed by non-empty strings. Keys

docs/consumers/pkg-promptkit.md

@@ -173,6 +173,29 @@ semantics. The
 [OpenAI-compatible integration contract](../integrations/openai-compatible-chat.md)
 owns the built-in client's outbound HTTP behavior.
 
+### Repair A Structured Result
+
+Set a small additional-call budget when a structurally invalid result can be
+corrected automatically:
+
+```go
+request.Validation = &promptkit.OutputContract{
+	Format:         promptkit.FormatJSON,
+	ValidationMode: promptkit.ValidationJSONSchema,
+	SchemaPath:     "events.schema.json",
+	RepairAttempts: 1,
+}
+```
+
+Each repair attempt is another model call, so it can increase latency and
+usage; `RunResult.Usage` is cumulative and `Validation.RepairAttempts` reports
+calls actually started. Exhaustion still returns the final failed validation
+result. `basic` validation can also repair an empty candidate, but structural
+validity is not evidence of factual or domain correctness. See the
+[output-contract format reference](../formats.md#output-contract) and
+[`OutputContract` GoDoc](../../types.go) for the exact budget and eligibility
+rules.
+
 ## Inputs, Profiles, And Overrides
 
 Use `File`, `Inline`, or `InlineWithURI` to construct request inputs. A request
@@ -189,6 +212,26 @@ For programmatic profiles,
 [`OpenAICompatibleProfile`](../../profiles.go) converts ordinary
 OpenAI-compatible settings into a value accepted by `WithProfiles`.
 
+### Alias A Built-In Profile
+
+Give an application-owned profile ID a built-in base when prompts should select
+the application ID while inheriting the built-in target. The child can override
+only the setting it owns:
+
+```go
+promptkit.WithProfiles(promptkit.Profile{
+	ID:              "weather-light",
+	BaseProfileID:   "deepseek-4-flash",
+	ReasoningEffort: "high",
+})
+```
+
+Select `weather-light` in a prompt or `RunRequest.ProfileID`; it remains the
+reported selected profile. See the [profile inheritance format
+reference](../formats.md#profile-inheritance) and the
+[`Profile` GoDoc](../../types.go) for exact lookup, merging, and validation
+behavior.
+
 ### Use The Rakestrawhome Built-In Profile
 
 Set `RAKESTRAWHOME_INFERENCE_API_KEY` in the application environment, then
@@ -231,7 +274,7 @@ if err != nil {
 
 target := inspection.EffectiveModelParams
 if target.APIKeyEnv != "" {
-	// Apply application policy for the named environment variable.
+	// This is a configured optional environment lookup source.
 } else if inspection.APIKeyRequired {
 	// Arrange a direct credential before later execution.
 }
@@ -240,9 +283,11 @@ if target.APIKeyEnv != "" {
 Use this configuration-time boundary when only the profile and its target need
 checking. Use `Prepare` when the application also needs prompt, input, schema,
 or rendering work; use prepared execution when that work must remain tied to a
-later execution. Inspection reports credential requirements but leaves the
+later execution. A reported `APIKeyEnv` is a configured optional source, while
-timing of credential enforcement to the application. The method's
+`APIKeyRequired` is the explicit local requirement. The
-[GoDoc](../../engine.go) owns its exact result and error contract.
+[credential format reference](../formats.md#credentials) and the method's
+[GoDoc](../../engine.go) own the exact precedence, timing, result, and error
+contracts.
 
 ### Set A Per-Run Session And Reasoning
 

docs/formats.md

@@ -126,7 +126,7 @@ outbound integration determines its wire representation.
 | `format` | yes | `text`, `markdown`, or `json`. |
 | `validation_mode` | yes | `none`, `basic`, `json`, or `json_schema`. |
 | `schema_path` | for `json_schema` | Path to a schema in the configured schema source. |
-| `repair_attempts` | no | Integer zero or greater; omitted means zero. |
+| `repair_attempts` | no | Integer from zero through three; omitted means zero. A positive value requires `basic`, `json`, or `json_schema` validation. |
 
 The validation modes behave as follows:
 
@@ -136,9 +136,15 @@ The validation modes behave as follows:
 - `json_schema` requires valid JSON that satisfies the selected schema.
 
 `format` controls output artifact metadata. JSON Schema mode also supplies the
-schema to compatible model clients as structured-output metadata. The public
+schema to compatible model clients as structured-output metadata. Plain `json`
-engine does not install an output repairer, so its validation is single-pass
+validation accepts every valid JSON value and does not request a provider-native
-even when a positive `repair_attempts` value is present.
+JSON-object constraint.
+
+`repair_attempts` counts additional generation calls after a failed validation.
+Zero is single-pass. With a positive eligible budget, Promptkit stops at the
+first valid candidate. If the budget is exhausted, it returns the final
+candidate and its complete failed validation result; generation and operational
+validation failures remain errors. `none` never permits repair.
 
 A request-level `OutputContract` replaces the complete prompt output contract.
 It does not merge individual fields. If its format is empty, Promptkit uses
@@ -173,9 +179,19 @@ extra_params:
   provider_option: enabled
 ```
 
+A derived profile can use a named base and override only the settings it owns:
+
+```yaml
+id: local-summary-fast
+base_profile: local-summary
+timeout_seconds: 30
+reasoning_effort: low
+```
+
 | Field | Required | Meaning |
 | --- | --- | --- |
 | `id` | yes | Profile identifier, trimmed before selection and publication. It must be non-empty after trimming and unique within one source after normalization. |
+| `base_profile` | no | One optional parent profile ID. A derived profile may inherit target fields from it. |
 | `backend` | unless `endpoint` is present | Backend registry ID. It is trimmed and registry membership is checked when the profile is prepared or inspected. |
 | `endpoint` | unless `backend` is present | OpenAI-compatible base URL, including an API version path when required. A nonempty value is trimmed and must be absolute HTTP or HTTPS with a host and without user information, a query, or a fragment. When both connection fields are present, this overrides the backend endpoint without changing backend identity. |
 | `model` | yes | Non-empty provider model name. |
@@ -185,12 +201,17 @@ extra_params:
 | `timeout_seconds` | no | Per-generation deadline in whole seconds; integer zero or greater. |
 | `service_tier` | no | Provider-specific request tier. |
 | `reasoning_effort` | no | Provider-specific reasoning setting. |
-| `api_key_env` | no | Name of an environment variable containing the API key. |
+| `api_key_env` | no | Optional environment-variable lookup source for an API key. |
 | `extra_params` | no | JSON-compatible provider-specific outbound fields. |
 
 Raw `api_key` is prohibited in profile YAML. Store only an environment
 variable name in `api_key_env`.
 
+A standalone profile must provide a model and at least one of `backend` or
+`endpoint`. A derived profile may omit those target fields because its selected
+base chain can provide them. Local parsing still validates a derived profile's
+own ID, supplied endpoint, execution-setting bounds, and `extra_params`.
+
 Promptkit does not infer a backend from a model or endpoint. Endpoint-only
 profiles remain supported and have no effective backend ID.
 The engine always provides the built-in `openrouter` and `rakestrawhome` IDs.
@@ -266,6 +287,32 @@ profiles. They use `APIKeyRequired` for request-scoped credentials instead of
 `api_key_env`. Preparation and exact profile inspection use this same source
 precedence.
 
+When a selected definition names `base_profile`, every profile ID in that
+chain is looked up through this same precedence order. A higher-precedence
+definition therefore shadows a lower-precedence definition of the same base
+ID, including a built-in. References are not source-qualified.
+
+### Profile Inheritance
+
+Promptkit resolves one linear base chain of at most 32 profiles, including the
+selected profile. It merges settings from the root base to the selected leaf.
+The leaf's `id` remains the selected profile identity. Nonblank string fields
+(`backend`, `endpoint`, `model`, `service_tier`, `reasoning_effort`, and
+`api_key_env`) and nonzero numeric fields replace inherited values. A nonempty
+`extra_params` map replaces the complete inherited map rather than merging
+keys, and `APIKeyRequired: true` remains true through the chain. Backend and
+endpoint are independent: replacing one does not clear the other.
+
+There is no profile-level clearing syntax. Blank strings, zero numbers, false,
+and empty maps remain unspecified and inherit from a base. Use existing
+presence-aware request overrides where an execution needs an explicit zero or
+empty reasoning setting.
+
+An absent directly selected profile reports the ordinary not-found error. Once
+the selected profile exists, a missing base, cycle, overlong chain, or
+incomplete resolved target is a profile-load failure. Ordinary operations
+resolve chains afresh; prepared execution retains the fully resolved target.
+
 ## Built-In Profile Catalog
 
 Every built-in profile selects one maintained built-in backend and inherits
@@ -318,16 +365,25 @@ schema produces a failed validation result.
 Credential values belong at the request or environment boundary, never in
 prompt, profile, schema, or example files:
 
-- a file profile names an environment variable with `api_key_env`;
+- a backend or file profile can name an optional environment lookup source
-- an in-memory profile may set `APIKeyRequired`;
+  with `APIKeyEnv` or `api_key_env`;
-- a request can provide a direct `APIKey` or override `APIKeyEnv`; and
+- an in-memory profile may set `APIKeyRequired` as an explicit local
+  requirement;
+- a request can provide a direct `APIKey` or override the optional `APIKeyEnv`
+  source; and
 - a direct request key takes precedence over environment lookup.
 
 After a direct request key, the credential-source precedence is request
 `APIKeyEnv`, profile `api_key_env`, then the backend default. An in-memory
 profile with `APIKeyRequired` clears an inherited backend environment name and
 requires a direct key unless the request explicitly supplies `APIKeyEnv`.
-Promptkit validates required credential availability during preparation.
+Named environment sources are optional: when the selected source is absent,
+empty, or whitespace-only, the built-in client omits the `Authorization`
+header and handles the provider response normally. `APIKeyRequired` is the
+only explicit local availability requirement. Promptkit validates required
+credential availability during preparation and rechecks it when a prepared
+execution runs. Injected clients receive resolved source metadata but define
+their own credential-resolution behavior.
 Direct keys are excluded from JSON results and redacted by public string
 formatters. Environment-variable names may appear in prepared metadata, but
 their values do not.

docs/integrations/openai-compatible-chat.md

@@ -31,11 +31,13 @@ does not serialize it in the provider request.
 
 ## Authentication
 
-A non-empty API key supplied directly on the execution target takes
+A usable API key supplied directly on the execution target takes precedence.
-precedence. Otherwise, when an API-key environment-variable name is supplied,
+Otherwise, when an API-key environment-variable name is supplied, the client
-the client reads that variable and requires a non-empty value. The selected
+reads and trims that variable. A bearer header is sent only when the resolved
-key is sent as `Authorization: Bearer <key>`. No authorization header is sent
+direct or environment credential is non-empty. When neither source is usable,
-when neither mechanism is configured.
+the client omits `Authorization` and handles the provider response normally.
+An explicitly required target with no usable source is rejected before
+transport.
 
 The target contains the already resolved environment-variable name: an
 explicit request override takes precedence over profile metadata, which takes
@@ -65,7 +67,8 @@ The client conditionally includes:
 - non-empty `service_tier` and effective `reasoning_effort`; an explicitly
   disabled reasoning setting is empty and therefore omitted; and
 - `response_format` for JSON Schema structured output, including its name,
-  strict flag, and schema document.
+  strict flag, and schema document. Plain JSON validation does not add an
+  object-only response constraint.
 
 The engine resolves backend, profile, and request extra-parameter maps by
 whole-map replacement rather than key merging. The resulting effective map is
@@ -97,10 +100,12 @@ drained.
 
 The bounded body must contain exactly one OpenAI-compatible JSON response
 object followed only by JSON whitespace and EOF. The client returns the first
-choice's non-empty message content and maps prompt, completion, total, cached,
+choice's explicitly present string message content, including an empty or
-and cache-write token counts. Invalid or truncated JSON, trailing non-whitespace
+whitespace-only string, and maps prompt, completion, total, cached, and
-data, a second JSON value, absent choices, empty first-choice content, and size
+cache-write token counts. Invalid or truncated JSON, trailing non-whitespace
-overflow are malformed responses and return no partial result.
+data, a second JSON value, absent choices, missing content, `null` content,
+non-string content, and size overflow are malformed responses and return no
+partial result.
 
 For a non-2xx status, Promptkit recognizes one JSON document with a top-level
 object-valued `error` member. Its optional `message` and `type` fields must be

docs/internal/llm.md

@@ -55,12 +55,14 @@ the target, rendered messages, and structured-output constraint retained by
 executable preparation. Execution does not reopen or rerender consumer
 sources.
 
-Before backend admission, the runner rechecks that the frozen credential
+Before backend admission, the runner rechecks a frozen credential
-environment-variable name is available. The handle does not retain the
+environment-variable name only when the target explicitly requires a
-environment value; the model client resolves the value visible when generation
+credential. The handle does not retain the environment value; the model client
-begins. A direct request key remains in private execution state only until the
+resolves the value visible when generation begins. For optional sources with no
-claimed execution finishes or an unclaimed handle is discarded. Exact public
+usable value, the built-in client omits `Authorization` and continues to the
-ownership and redaction semantics belong to the
+provider. A direct request key remains in private execution state only until
+the claimed execution finishes or an unclaimed handle is discarded. Exact
+public ownership and redaction semantics belong to the
 [`PreparedExecution` GoDoc](../../prepared_execution.go).
 
 ## Failure Categories
@@ -68,12 +70,18 @@ ownership and redaction semantics belong to the
 The package preserves distinct error identities for invalid client
 configuration, invalid generation requests, request execution failures,
 non-success provider statuses, and malformed successful responses. Provider
-response bodies are not included in non-success errors.
+response bodies are never exposed in raw form through non-success errors.
 
 Invalid nonempty configured endpoints are configuration failures. A missing or
 invalid final selected endpoint is an invalid generation request and is
 rejected before transport.
 
+Authentication resolves a trimmed direct key before a trimmed configured
+environment value. Optional missing, empty, or whitespace-only sources do not
+block transport and produce no `Authorization` header. An explicitly required
+target with no usable source is rejected before transport with the existing
+invalid-request diagnostics.
+
 Successful response bodies have a fixed 16 MiB limit enforced by declared
 length and by reading at most one byte beyond the boundary. The decoder accepts
 exactly one JSON object plus trailing whitespace and EOF. Size overflow,
@@ -81,6 +89,12 @@ truncation, malformed JSON, trailing data, and a second value are malformed
 responses with no partial result or provider content in the error. Every body
 is closed, and an unbounded oversized stream is not drained.
 
+After framing succeeds, the first choice must contain an explicitly present
+string `message.content`. The string is returned exactly, including empty or
+whitespace-only content. Missing choices, missing or `null` content, and
+non-string content are malformed responses. Output validation and correction
+eligibility remain outside this package.
+
 For a non-success response, `ProviderHTTPError` retains the HTTP status and
 only normalized detail from the bounded recognized envelope. It retains
 `ErrUnexpectedStatus` through unwrapping. The client owns response closure;

docs/internal/overview.md

@@ -11,7 +11,7 @@ contributor workflow and validation.
 
 | Component | Implemented responsibility | References |
 | --- | --- | --- |
-| Root `promptkit` package | Provides the supported engine facade, source, backend-registration, and injection options, public request, result, prompt-inspection, and profile-inspection values, opaque prepared-execution handles, profile construction, extension interfaces, value conversion, redacted formatting, typed capacity and generation error mapping, and engine-local profile-source assembly including application fallbacks. | [Package GoDoc](../../doc.go), [prepared execution](../../prepared_execution.go), [backend API](../../backends.go), [engine assembly](../../engine.go) |
+| Root `promptkit` package | Provides the supported engine facade, source, backend-registration, and injection options, public request, result, prompt-inspection, and profile-inspection values, opaque prepared-execution handles, profile construction, extension interfaces, value conversion, redacted formatting, typed capacity and generation error mapping, engine-local profile-source assembly including application fallbacks, and bounded output-repair assembly. | [Package GoDoc](../../doc.go), [prepared execution](../../prepared_execution.go), [backend API](../../backends.go), [engine assembly](../../engine.go) |
 | `examples/go-library/prepare` | Demonstrates an offline downstream consumer using a prompt file, in-memory profile, inline input, and `Prepare`. It is not a public library package. | [Example program](../../examples/go-library/prepare/main.go) |
 | `examples/go-library/run` | Demonstrates an offline downstream consumer using a prompt file, in-memory profile, inline input, an injected deterministic model client, and `Run`. It is not a public library package. | [Example program](../../examples/go-library/run/main.go) |
 | `internal/backend` | Constructs each engine's immutable registry from the maintained built-in definitions and consumer additions, validates and defensively copies definitions through the shared JSON-value package, and consumes the LLM-owned OpenAI-compatible reserved request-field rule. | [Backend registry](../../internal/backend/registry.go) |
@@ -21,13 +21,13 @@ contributor workflow and validation.
 | `internal/filecatalog` | Provides deterministic YAML discovery and path helpers for operating-system filesystems and `fs.FS` sources. | [File catalog](../../internal/filecatalog/catalog.go) |
 | `internal/jsonvalue` | Validates and deeply copies bounded JSON-compatible extra-parameter and prepared-schema trees while preserving supported concrete value types and rejecting cycles or excessive depth and work. | [JSON values](../../internal/jsonvalue/jsonvalue.go) |
 | `internal/promptdef` | Loads strictly decoded, validated prompt definitions from filesystem and `fs.FS` sources, including version selection and contained file-backed message content. | [Framework formats](../formats.md), [prompt-definition repository](../../internal/promptdef/filesystem_repository.go) |
-| `internal/profile` | Loads strictly decoded, validated execution profiles, including backend selection, from filesystem and `fs.FS` sources and composes repositories with error-preserving fallback. | [Framework formats](../formats.md), [profile repositories](../../internal/profile/filesystem_repository.go) |
+| `internal/profile` | Loads strictly decoded, locally validated execution profiles from filesystem and `fs.FS` sources, overlays raw sources with error-preserving fallback, and resolves inherited profiles. | [Framework formats](../formats.md), [profile repositories](../../internal/profile/filesystem_repository.go), [internal sources](sources.md#profiles-and-built-ins) |
 | `internal/profile/builtin` | Embeds the built-in profile catalog, whose entries select maintained built-in backends. | [Built-in catalog](../formats.md#built-in-profile-catalog), [repository](../../internal/profile/builtin/repository.go) |
 | `internal/prompt` | Renders prompt messages from Go templates with artifact, variable, session, and cache-control data. | [Go-template renderer](../../internal/prompt/go_renderer.go) |
 | `internal/artifact` | Resolves ordinary inline and unrestricted caller-selected file references into copied artifacts with metadata and hashes. | [Internal sources and validation](sources.md) |
 | `internal/validate` | Validates basic, JSON, and JSON Schema output using operating-system filesystem or `fs.FS` schema sources and creates operation-local validation plans with canonical contained schema resources. | [Framework formats](../formats.md#schemas), [internal sources and validation](sources.md) |
 | `internal/llm` | Defines the internal generation boundary and implements outbound OpenAI-compatible chat requests from resolved execution targets, including bounded structured non-success response decoding, successful-response decoding, authentication, deadline handling, and ownership of the OpenAI-compatible reserved request-field policy. | [Internal model client](llm.md) |
-| `internal/usecase` | Resolves prompt definitions and hashes, profiles, backends, and targets for exact inspection and request settings for preparation, and coordinates ordinary execution and one-attempt prepared execution across internal sources, rendering, artifact loading, operation-local validation plans, generation, capacity, and optional repair. | [Internal runner](runner.md), [prepared-execution implementation](../../internal/usecase/prepared_execution.go) |
+| `internal/usecase` | Resolves prompt definitions and hashes, profiles, backends, and targets for exact inspection and request settings for preparation, and coordinates ordinary execution and one-attempt prepared execution across internal sources, rendering, artifact loading, operation-local validation plans, generation, capacity, and bounded repair. | [Internal runner](runner.md), [prepared-execution implementation](../../internal/usecase/prepared_execution.go) |
 
 The root package assembles these internal components without exposing their
 representations. Consumers depend only on the root facade.

docs/internal/runner.md

@@ -23,8 +23,10 @@ built-in backend and validated consumer additions, one engine-local run
 admitter, and a model client wrapped by the same capacity manager. Validation
 plans and provider-facing schema metadata come from the validator's preparation
 interface.
-An output repairer can be injected internally, but the ordinary runner
+The root engine supplies one default output repairer through the explicit
-constructor does not enable one.
+runner constructor, using the same capacity-wrapped client as initial
+generation. The no-repair runner constructor remains available for focused
+internal callers and tests.
 
 Each invocation carries its state in request, prepared-run, and result values.
 The runner has no durable run or session store.
@@ -125,8 +127,8 @@ admitter is an internal unlimited fallback. After successful admission, `Run`
 immediately defers the returned release function, performs the completion
 phase, makes one initial generation call, builds the named output artifact,
 and validates that artifact with the plan compiled during completion. Invalid
-generated content remains a validation result; an inability to perform
+generated content remains a validation result; an inability to generate or
-validation is an operational error.
+perform validation is an operational error.
 
 Validation preparation and execution honor cancellation at every
 Promptkit-controlled boundary and do not publish a partial plan or result.
@@ -142,17 +144,25 @@ serializing preparation or validation behind the active-generation limit.
 The wrapped model client separately acquires a FIFO active permit only around
 each actual generation call.
 
-When an internal repairer is present, a JSON or JSON Schema content failure can
+After a failed `basic`, JSON, or JSON Schema validation with a positive frozen
-trigger bounded repair attempts. Repair receives the effective execution
+budget, the installed repairer can make a bounded corrective call. Each request
-target, explicit numeric-presence bits, credential, backend identity, session
+starts with a fresh copy of the complete original rendered messages, includes
-ID, validation errors, prior output, and structured-output specification. One
+only the latest nonempty candidate as an assistant message, and appends one
-request constructor supplies those common fields to initial and repair
+corrective user message. Empty candidates omit that assistant message. The
-generation while their rendered prompts remain intentionally distinct. The
+correction carries validation diagnostics as JSON data bounded to 64 KiB; the
-default repairer uses the same wrapped client as initial generation, so each
+full diagnostics remain in the validation result.
-repair reacquires the selected backend's active permit while remaining inside
+
-its original admission lease. Repair never performs a second bounded
+Repair receives the effective execution target, explicit numeric-presence bits,
-admission, and repaired outputs use the operation's existing validation plan.
+credential, backend identity, session ID, and structured-output specification.
-This capability remains internal and is not a public option.
+The same request constructor supplies those common fields to initial and repair
+generation. 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. The runner stops at the first valid candidate, sums completed
+generation usage, reports calls actually started, and returns the final failed
+validation result on exhaustion. A repair generation failure follows the
+ordinary generation-error category rather than becoming a validation error.
 
 A successful result includes the output artifact and raw output, validation
 state, effective session ID, prompt and rendered-prompt hashes, selected

docs/internal/sources.md

@@ -39,17 +39,17 @@ duplicate detection, and source containment:
 
 ## Profiles And Built-Ins
 
-`internal/profile` loads and validates execution profiles from an
+`internal/profile` loads, locally validates, overlays, and resolves execution
-operating-system filesystem or an `fs.FS`. A file contains exactly one YAML
+profiles from an operating-system filesystem or an `fs.FS`. A file contains
-document and its trimmed YAML `id` is its only selection identity; filenames do
+exactly one YAML document and its trimmed YAML `id` is its only selection
-not confer authority. Each point lookup reads discovered files once for their
+identity; filenames do not confer authority. Each point lookup reads discovered
-metadata and reuses the selected file's bytes for strict decoding; unrelated
+files once for their metadata and reuses the selected file's bytes for strict
-profiles are not fully decoded. Strict selected decoding recognizes the
+decoding; unrelated profiles are not fully decoded. Strict selected decoding
-optional `backend` field, trims its value, and requires a model plus at least
+recognizes `base_profile` and the optional `backend` field, trims their values,
-one non-blank backend or endpoint. File-backed `extra_params` values are
+and permits inherited target fields only when a base is named. File-backed
-validated and defensively copied through the shared bounded JSON-value owner
+`extra_params` values are validated and defensively copied through the shared
-before a profile is published. OpenAI-compatible reserved-field policy remains
+bounded JSON-value owner before a profile is published. OpenAI-compatible
-with the model-client and backend-registry owners.
+reserved-field policy remains with the model-client and backend-registry owners.
 
 The overlay repository consults the next repository only when the
 higher-precedence repository reports that a profile is absent. A reliably
@@ -59,14 +59,25 @@ backend registry membership because the available registry belongs to the
 assembled engine; the runner checks membership during preparation and exact
 profile inspection.
 
-The root engine assembles profile repositories in precedence order: in-memory
+The root engine assembles one raw composite catalog in precedence order:
-profiles, one ordinary configured source, an application fallback source, then
+in-memory profiles, one ordinary configured source, an application fallback
-the embedded built-in catalog. An explicit file or `fs.FS` profile source
+source, then the embedded built-in catalog. An explicit file or `fs.FS` profile
-replaces `Config.ProfileDir` within the ordinary configured-source category.
+source replaces `Config.ProfileDir` within the ordinary configured-source
+category. One outer resolving repository wraps that complete raw catalog, so
+each base lookup observes the same precedence and shadowing rules.
 
-Exact profile inspection performs one point-in-time lookup through those
+The resolving repository traverses every selected chain afresh, retains no
-profile sources and checks the resolved target without reading prompt, input,
+cache, detects cycles, limits a chain to 32 profiles, merges root-to-leaf into a
+new caller-owned value, and validates the final target before publishing it. It
+does not check backend registry membership. Exact `base_profile` syntax, merge
+rules, and consumer-visible failure behavior belong to the [framework format
+reference](../formats.md#profile-inheritance).
+
+Exact profile inspection performs one point-in-time resolved lookup through
+those profile sources and checks the final target without reading prompt, input,
 or schema sources. It does not retain that lookup for a later execution.
+Prepared execution instead freezes the fully resolved target; a later ordinary
+operation performs a fresh traversal.
 
 `internal/profile/builtin` embeds the maintained built-in profile catalog.
 Every embedded profile selects a maintained built-in backend and inherits that

docs/releases/v0.7.0.md

@@ -0,0 +1,155 @@
+# Promptkit v0.7.0
+
+This supplemental changelog and migration guide summarizes the consumer-facing
+changes from `v0.6.0` to `v0.7.0`. The annotated `v0.7.0` tag is the
+authoritative release record. Exact current contracts belong to the linked
+GoDoc and durable documentation.
+
+## Summary
+
+`v0.7.0` expands provider integration and profile composition while making
+credential and generation-failure handling more flexible:
+
+- Promptkit now includes the `rakestrawhome` backend and its Gemma profile;
+- built-in generation failures expose bounded structured provider details;
+- an unavailable optional API-key environment source no longer prevents a
+  request from reaching an upstream that permits unauthenticated access; and
+- profiles can inherit from and selectively refine another profile.
+
+## Compatibility
+
+This release adds public declarations and fields but removes none. Existing
+keyed configuration literals and ordinary `errors.Is` handling continue to
+work.
+
+Adding `BaseProfileID` to `Profile` and `OpenAICompatibleProfileConfig` changes
+their struct shape. Consumers using positional composite literals for either
+type must convert them to keyed literals. Existing keyed literals require no
+change.
+
+The `rakestrawhome` backend ID is now built in and reserved. A consumer that
+previously registered that exact ID with `WithBackend` must remove its manual
+registration before upgrading. Other custom backend registrations are
+unchanged.
+
+When an optional backend, profile, or request `APIKeyEnv` is unset, empty, or
+whitespace-only, the built-in client now omits `Authorization` and sends the
+request. Previously this condition could fail before transport. Set
+`Profile.APIKeyRequired` when missing credentials must remain a local
+preflight error.
+
+Provider non-success responses continue to match `ErrLLMGenerate`. Their
+rendered wording is not a compatibility contract; consumers can now use
+`errors.As` with `*GenerationError` when structured status information is
+needed.
+
+## Upgrade
+
+Update the module dependency with:
+
+```sh
+go get gitea.maximumdirect.net/eric/promptkit@v0.7.0
+go mod tidy
+```
+
+Remove any manual `rakestrawhome` backend registration, convert positional
+profile literals to keyed literals, and run the consuming project's ordinary
+and race-enabled tests.
+
+## Rakestrawhome Built-In Backend And Profile
+
+Every engine now includes the reserved `rakestrawhome` backend, identified by
+`BackendRakestrawHome`. The built-in `rakestrawhome-gemma-4-31b` profile
+selects that backend. Consumers can use the maintained endpoint, credential,
+capacity, and model defaults without registering either definition themselves.
+
+See the [built-in backend and profile catalogs](../formats.md#built-in-backends)
+and the [consumer adoption example](../consumers/pkg-promptkit.md#use-the-rakestrawhome-built-in-profile)
+for the current contracts.
+
+## Structured Generation Errors
+
+Non-2xx responses from the built-in OpenAI-compatible client now return an
+immutable `*GenerationError`. Consumers can inspect the HTTP status and any
+safely extracted provider code, type, or message while retaining the ordinary
+generation-error category:
+
+```go
+var generationErr *promptkit.GenerationError
+if errors.As(err, &generationErr) {
+	status := generationErr.StatusCode()
+	_ = status
+}
+```
+
+Provider fields are bounded and normalized but remain untrusted and may
+contain sensitive request or schema details. Default and Go-syntax formatting
+omit those fields. Applications must apply their own disclosure policy before
+logging or presenting accessor values.
+
+See the [`GenerationError` GoDoc](../../generation_error.go), the
+[consumer error-handling guide](../consumers/pkg-promptkit.md#handle-errors),
+and the [OpenAI-compatible response contract](../integrations/openai-compatible-chat.md#response-handling).
+
+## Optional Credential Sources
+
+`APIKeyEnv` names an optional environment lookup source unless the selected
+profile explicitly sets `APIKeyRequired`. When neither a direct request key nor
+a usable environment value exists, the built-in client omits the bearer header
+and handles the upstream response normally. This supports local and other
+OpenAI-compatible providers that permit unauthenticated requests without
+hiding an authentication error returned by a provider that requires one.
+
+The [credential format reference](../formats.md#credentials), the
+[`Backend` GoDoc](../../backends.go), the
+[`ExecutionTargetOverride` GoDoc](../../types.go), and the
+[authentication integration contract](../integrations/openai-compatible-chat.md#authentication)
+define the current precedence and availability rules.
+
+## Profile Inheritance
+
+YAML profiles can name one parent with `base_profile`; in-memory profiles use
+`Profile.BaseProfileID`, and `OpenAICompatibleProfileConfig` forwards the same
+field. A profile can act as an application-owned alias of a built-in or refine
+selected inherited settings:
+
+```go
+promptkit.WithProfiles(promptkit.Profile{
+	ID:              "weather-light",
+	BaseProfileID:   "deepseek-4-flash",
+	ReasoningEffort: "high",
+})
+```
+
+Base lookup observes the existing source precedence. Chains are linear,
+cycle-safe, and resolved afresh for ordinary operations. Prepared execution
+freezes the fully resolved target. The selected leaf ID remains public while
+effective execution settings reflect the resolved chain.
+
+See the [profile inheritance format reference](../formats.md#profile-inheritance),
+the [consumer alias example](../consumers/pkg-promptkit.md#alias-a-built-in-profile),
+and the [`Profile` GoDoc](../../types.go) for exact merge and validation
+behavior.
+
+## Public API Changes
+
+The release adds:
+
+- `BackendRakestrawHome`;
+- `GenerationError`, including `StatusCode`, `ProviderCode`, `ProviderType`,
+  `ProviderMessage`, `Error`, `GoString`, and `Unwrap`;
+- `Profile.BaseProfileID`; and
+- `OpenAICompatibleProfileConfig.BaseProfileID`.
+
+No public declaration was removed.
+
+## Consumer Action
+
+- Remove a manual backend registration whose ID is exactly `rakestrawhome`.
+- Convert positional `Profile` or `OpenAICompatibleProfileConfig` literals to
+  keyed literals.
+- Set `Profile.APIKeyRequired` where a missing credential must fail locally
+  instead of reaching the provider unauthenticated.
+- Treat `GenerationError` provider fields as untrusted and potentially
+  sensitive when adopting the new accessors.
+- Run consumer ordinary and race-enabled tests after updating the module.

docs/releases/v0.8.0.md

@@ -0,0 +1,109 @@
+# Promptkit v0.8.0
+
+This supplemental changelog and migration guide summarizes the consumer-facing
+changes from `v0.7.0` to `v0.8.0`. The annotated `v0.8.0` tag is the
+authoritative release record. Exact current contracts belong to the linked
+GoDoc and durable documentation.
+
+## Summary
+
+`v0.8.0` activates Promptkit's bounded output-repair workflow:
+
+- failed nonempty-text, JSON, and JSON Schema validation can make a limited
+  number of corrective model calls;
+- corrective calls preserve the original rendered conversation, effective
+  target, session, structured-output contract, and backend capacity policy;
+- results report cumulative usage and the number of corrective calls actually
+  made; and
+- explicitly empty OpenAI-compatible response content now reaches output
+  validation instead of being classified as a malformed provider envelope.
+
+## Compatibility
+
+This release adds no public declarations or fields and removes none. Existing
+source code remains source-compatible.
+
+The behavior of the existing `OutputContract.RepairAttempts` field and prompt
+YAML `repair_attempts` field has changed. A positive value now authorizes real
+additional model calls after eligible validation failures; earlier releases
+accepted the field but the public engine remained single-pass. Consumers that
+set a positive value should expect additional latency, token usage, and
+provider cost when repair is needed.
+
+Repair budgets must now be between zero and three. A positive budget requires
+`basic`, `json`, or `json_schema` validation. Values above three and a positive
+budget paired with `none` are invalid contracts rather than ignored settings.
+
+An explicitly present empty or whitespace-only string returned by the built-in
+OpenAI-compatible client is now a completed generation candidate. `none`
+validation permits it, while `basic`, `json`, and `json_schema` classify it
+under their ordinary validation rules and may repair it when configured.
+Missing, `null`, or non-string content remains a malformed provider response.
+
+## Upgrade
+
+Update the module dependency with:
+
+```sh
+go get gitea.maximumdirect.net/eric/promptkit@v0.8.0
+go mod tidy
+```
+
+Review every prompt definition and request override that sets a positive repair
+budget. Use zero or omit the field to retain single-pass execution. Ensure each
+positive budget is no greater than three and uses an eligible validation mode,
+then run the consuming project's ordinary and race-enabled tests.
+
+## Bounded Output Repair
+
+`repair_attempts` counts corrective calls in addition to the initial model
+call. Promptkit validates each completed candidate, stops at the first valid
+one, and never exceeds the configured bound. If every candidate remains
+invalid, the run completes successfully with the final candidate and its
+failed validation result rather than returning an operational error.
+
+Each correction starts from the original rendered messages and includes only
+the latest invalid candidate and latest validation diagnostics. JSON Schema
+mode retains the provider-native structured-output request as its first line of
+defense. Promptkit performs only deterministic structural validation; a valid
+response is not necessarily factual or correct for an application's domain.
+
+Usage in the final result is cumulative across the initial response and every
+completed corrective response. `ValidationResult.RepairAttempts` reports the
+number of corrective calls actually made. Corrective generation failures use
+the same public generation-error categories and structured provider details as
+an initial generation failure.
+
+See the [output-contract format reference](../formats.md#output-contract), the
+[consumer repair example](../consumers/pkg-promptkit.md#repair-a-structured-result),
+and the [`OutputContract` and `ValidationResult` GoDoc](../../types.go) for the
+current contracts.
+
+## Explicit Empty Content
+
+The built-in OpenAI-compatible client now distinguishes an explicitly present
+empty string from a missing or malformed `content` field. This aligns built-in
+and injected clients by letting the selected output contract decide whether an
+empty candidate is acceptable, invalid, or eligible for repair.
+
+See the
+[OpenAI-compatible response contract](../integrations/openai-compatible-chat.md#response-handling)
+for the exact envelope behavior.
+
+## Public API Changes
+
+None. This release activates and tightens the documented behavior of existing
+fields.
+
+## Consumer Action
+
+- Remove or set `repair_attempts` to zero where execution must remain
+  single-pass.
+- Keep every positive repair budget at three or fewer and pair it with
+  `basic`, `json`, or `json_schema` validation.
+- Account for additional latency, usage, and provider cost when enabling
+  repair.
+- Continue checking the returned validation status because bounded repair can
+  exhaust without producing a valid candidate.
+- Review workflows that previously treated explicit empty provider content as
+  a generation error.

docs/roadmap/future.md

@@ -38,33 +38,8 @@ consumers.
 
 ## Ideas
 
-### Public bounded output repair
+No ideas are currently awaiting selection. Active feature work belongs in its
-
+focused roadmap rather than this catalog.
-After the codebase-audit remediations are complete, Promptkit should make its
-bounded output-repair capability available through the public engine. A
-consumer should be able to request a limited number of corrective generation
-attempts when JSON or JSON Schema output fails content validation, without
-having to reproduce Promptkit's generation, validation, capacity, and result-
-accounting orchestration.
-
-- Repair is validation recovery, not a general provider retry, failover, or
-  backoff policy. Transport failures, cancellation, and operational schema or
-  validation errors must retain their ordinary error behavior.
-- Repair must stop after the first valid result or the configured attempt
-  bound. Exhausting the bound should preserve the final invalid result and its
-  validation diagnostics rather than inventing success.
-- Initial generation and every repair attempt must use the same resolved
-  backend, effective execution settings and presence semantics, session,
-  credential boundary, structured-output contract, and backend-capacity
-  policy.
-- Results should report the number of repair attempts and cumulative usage for
-  every model call made by the run.
-- Ordinary and prepared execution should expose coherent behavior, including
-  cancellation, frozen prepared state, error identity, and capacity lifetime.
-
-Select this work only after the accepted audit findings affecting shared
-execution invariants, validation, orchestration, transport, and repair
-internals have been remediated.
 
 ## Entry Format
 

docs/roadmap/implementation.md

@@ -1,437 +0,0 @@
-# Structured Generation Errors Implementation Plan
-
-## Purpose
-
-Implement the target state defined in the
-[structured generation errors roadmap](structured-generation-errors.md): turn
-every non-2xx response from the built-in OpenAI-compatible client into a
-bounded, immutable public error that exposes deliberate provider diagnostics
-through `errors.As` while retaining `ErrLLMGenerate` through `errors.Is`.
-
-This document owns implementation sequencing. The feature roadmap owns the
-consumer intent, public-policy decisions, safety limits, compatibility
-boundaries, and non-goals. Follow the architecture, documentation, and testing
-policies under [`docs/policy/`](../policy/) throughout the work.
-
-## Fixed Decisions
-
-- The public type is `GenerationError`. Engine-produced values are pointers;
-  fields are unexported; no public constructor or mutation API is added.
-- Public methods are `StatusCode() int`, `ProviderCode() string`,
-  `ProviderType() string`, `ProviderMessage() string`, `Error() string`,
-  `GoString() string`, and `Unwrap() error`.
-- Public `Unwrap` returns `ErrLLMGenerate`. Accessors, formatting, and unwrapping
-  are safe on a nil receiver and a zero value.
-- Engine-produced `Error()` text is exactly
-  `failed to generate output: provider returned HTTP status N`, where `N` is
-  the received status. A nil receiver or zero status returns exactly
-  `failed to generate output`. `GoString()` returns the same redacted text as
-  `Error()` so `%#v` cannot reveal unexported provider fields.
-- Default formatting contains no provider-controlled code, type, message, or
-  raw response content. The type has no stable JSON representation.
-- The recognized body is one JSON document with a top-level object-valued
-  `error`. `message` and `type` accept strings; `code` accepts a string or an
-  exact `json.Number`; supported fields are independent and unknown fields are
-  ignored.
-- The non-success-body limit is 65,536 bytes. Declared oversize bodies are not
-  read; other bodies are read through a 65,537-byte bound. Oversize, malformed,
-  unrecognized, or unreadable bodies produce status-only detail.
-- Normalization converts invalid UTF-8, collapses Unicode whitespace, control,
-  and format-character runs to one ASCII space, trims the result, omits blank
-  values, and produces one-line strings.
-- Codes and types longer than 256 Unicode code points are omitted. Messages
-  longer than 4,096 code points retain the first 4,095 code points followed by
-  `…`, for a total limit of 4,096.
-- Only the concrete built-in transport error is converted into a new public
-  `GenerationError`. Arbitrary injected-client errors are never inspected or
-  enriched.
-- The use-case and domain layers remain provider-neutral. No retryability,
-  retry, logging, presentation, provider-specific envelope, header, or success-
-  response behavior is added.
-
-## Execution Rules
-
-- Complete the stages in numerical order. Each stage is scoped for one
-  gpt-5.6-terra implementation prompt and must finish its focused tests before
-  the next begins.
-- Treat all stages as one feature delivery. Intermediate stages intentionally
-  create internal machinery before exposing it; do not release, tag, or claim
-  the feature is available until Stage 5 is complete.
-- At the start of each stage, reread the feature roadmap and the task-specific
-  references in [`docs/development.md`](../development.md). Preserve unrelated
-  working-tree changes.
-- Use classical behavior tests at the narrowest owner. Table-drive parser and
-  boundary cases, use controlled transports or local servers, and do not
-  duplicate the internal envelope matrix at the root engine boundary.
-- Do not contact a live provider, add dependencies, commit, tag, push, or edit
-  release documentation unless separately instructed.
-- Current-state prose documentation changes in Stage 5. Public GoDoc changes
-  alongside the public declarations in Stage 4 because GoDoc owns that API.
-
-## Stage 1: Add the Internal Structured Status Error and Envelope Parser
-
-### Objective
-
-Create the transport-owned structured value and pure parsing and normalization
-logic without changing `OpenAICompatibleClient.Generate` yet.
-
-### Implementation
-
-1. Add `internal/llm/provider_http_error.go`. Keep all provider HTTP mechanics
-   in `internal/llm`; do not add an HTTP error DTO to `internal/domain` or
-   `internal/usecase`.
-2. Define these private constants:
-   - `maxProviderErrorResponseBytes int64 = 64 << 10`;
-   - `maxProviderErrorIdentifierRunes = 256`; and
-   - `maxProviderErrorMessageRunes = 4096`.
-3. Add an exported-within-`internal` `ProviderHTTPError` type with unexported
-   `statusCode`, `providerCode`, `providerType`, and `providerMessage` fields.
-   The root facade will need to name this concrete type in Stage 4, but no
-   representation is public outside the module's `internal` boundary.
-4. Give `ProviderHTTPError` nil-safe read-only accessors with the same four
-   names as the planned public type. Implement:
-   - `Error()` as `llm returned non-success status: status=N` when status is
-     nonzero and `llm returned non-success status` otherwise;
-   - `GoString()` by returning `Error()`; and
-   - `Unwrap()` by returning `ErrUnexpectedStatus`.
-   Never include provider-derived strings in either formatter.
-5. Add a private `providerErrorDetails` value and a private constructor that
-   builds `*ProviderHTTPError` from a status plus already normalized details.
-6. Add `parseProviderErrorEnvelope([]byte) providerErrorDetails` with these
-   rules:
-   - use `json.Decoder` with `UseNumber` and require EOF after trailing JSON
-     whitespace;
-   - require a top-level object and object-valued `error` member;
-   - retain supported fields as `json.RawMessage` so each can be decoded and
-     validated independently;
-   - accept string `message` and `type` values;
-   - accept string or `json.Number` `code`, preserving validated number text
-     without float conversion;
-   - ignore unknown fields and treat invalid supported-field values as absent;
-     and
-   - return empty details for malformed framing, a missing or invalid `error`
-     object, or an object with no usable fields.
-7. Add private normalization helpers that implement the roadmap's UTF-8,
-   single-line, whitespace/control/format handling and exact rune limits. Use
-   rune-aware operations; do not truncate bytes in the middle of UTF-8. Omit
-   overlong code and type identifiers, and truncate overlong messages to 4,095
-   code points plus `…`.
-
-### Tests
-
-Add `internal/llm/provider_http_error_test.go` in package `llm` with focused,
-table-driven tests:
-
-1. `TestProviderHTTPErrorEnvelopeParsing` covers:
-   - all supported string fields;
-   - string, integer, fractional, and exponent-form numeric codes without
-     float coercion;
-   - `null` and invalid field types handled independently;
-   - unknown top-level and nested fields;
-   - missing, null, scalar, and empty `error` values;
-   - malformed, truncated, trailing-garbage, and second-document input; and
-   - no raw or unsupported metadata retained.
-2. `TestProviderErrorTextNormalizationAndLimits` covers valid multibyte text,
-   invalid UTF-8 replacement, leading/trailing and repeated whitespace,
-   newline/tab/control/format characters, blank normalization, exact identifier
-   and message boundaries, identifier omission one rune over, and rune-safe
-   message ellipsis one rune over.
-3. `TestProviderHTTPErrorIdentityAndFormatting` covers exact accessors,
-   `errors.Is(err, ErrUnexpectedStatus)`, nil receivers, zero values, and safe
-   `%v`, `%+v`, and `%#v` formatting with distinctive provider markers absent.
-
-Do not test body reading, HTTP response ownership, the root public type, or
-assembled engine behavior in this stage.
-
-### Verification
-
-```sh
-go test ./internal/llm -run 'TestProvider'
-go test ./internal/llm
-go test ./...
-```
-
-Stage 1 is complete when the parser and internal error are fully protected but
-the live non-2xx branch remains unchanged.
-
-**Status:** Complete.
-
-## Stage 2: Add the Bounded Non-Success Body Reader
-
-### Objective
-
-Implement and test bounded response-body extraction independently from HTTP
-client integration, keeping status preservation separate from envelope
-validity.
-
-### Implementation
-
-1. In `internal/llm/provider_http_error.go`, add a private helper with the
-   equivalent contract of:
-
-   ```go
-   func providerHTTPErrorFromBody(
-       statusCode int,
-       contentLength int64,
-       body io.Reader,
-   ) *ProviderHTTPError
-   ```
-
-2. Always return a nonnil `ProviderHTTPError` carrying `statusCode`.
-3. When `contentLength` is greater than 65,536, return status-only detail
-   without reading `body`.
-4. Otherwise read through an `io.LimitedReader` capped at 65,537 bytes. Return
-   status-only detail on a read error or when the extra byte is consumed. Do
-   not parse a bounded prefix of an incomplete oversized body.
-5. For a complete body at or below the limit, call
-   `parseProviderErrorEnvelope` and construct the error from its normalized
-   details.
-6. The helper does not close or drain `body`; the HTTP caller retains response-
-   body ownership. It must never read beyond the one-byte overflow probe.
-
-### Tests
-
-Extend `internal/llm/provider_http_error_test.go` with
-`TestProviderHTTPErrorBodyBounds`, using counting, failing, and guarded readers
-instead of an HTTP server. Cover:
-
-- an ordinary recognized envelope;
-- an exact 65,536-byte body, using trailing JSON whitespace to reach the
-  boundary while remaining one valid document;
-- a declared 65,537-byte body with zero reads;
-- unknown-length and underreported 65,537-byte bodies with exactly 65,537 bytes
-  read and status-only detail;
-- an early read failure with status-only detail; and
-- an empty body with status-only detail.
-
-Assert the provider markers are absent whenever extraction is discarded. Do
-not add body-closure assertions here because this helper does not own closing.
-
-### Verification
-
-```sh
-go test ./internal/llm -run 'TestProviderHTTPErrorBodyBounds|TestProvider'
-go test ./internal/llm
-go test ./...
-```
-
-Stage 2 is complete when every read path is deterministically bounded and the
-HTTP client's current branch is still untouched.
-
-**Status:** Complete.
-
-## Stage 3: Integrate Structured Status Errors into the Built-In Client
-
-### Objective
-
-Replace the built-in client's status-only discard branch with the bounded
-internal error while preserving all successful, cancellation, transport, and
-body-ownership behavior.
-
-### Implementation
-
-1. In `internal/llm/openai_compatible_client.go`, replace the non-2xx branch's
-   4,096-byte discard and formatted sentinel with
-   `providerHTTPErrorFromBody(httpResp.StatusCode, httpResp.ContentLength,
-   httpResp.Body)`.
-2. Keep the existing `defer httpResp.Body.Close()` as the single body-closure
-   owner. Do not close in the helper, drain after the bound, or reuse the 16 MiB
-   successful-response decoder or limit.
-3. Return no partial `GenerateResponse` for every non-2xx response.
-4. Preserve `errors.Is(err, ErrUnexpectedStatus)` through
-   `ProviderHTTPError.Unwrap`. Do not change `requestFailedError`, endpoint or
-   request validation, authentication, timeout handling, successful response
-   decoding, or response-size behavior.
-
-### Tests
-
-1. Update the existing non-success case in
-   `internal/llm/openai_compatible_client_test.go` to assert
-   `errors.As(err, &providerHTTPError)`, exact status, and continued
-   `ErrUnexpectedStatus` identity. Keep the existing raw-body redaction check.
-2. Add `internal/llm/provider_http_error_transport_test.go` with:
-   - `TestOpenAICompatibleClientStructuredNonSuccessResponse`, proving a
-     recognized envelope supplies all normalized internal fields and returns
-     no generation result;
-   - `TestOpenAICompatibleClientNonSuccessBodyOwnership`, table-driving normal,
-     declared-oversize, streamed-oversize, underreported, malformed, and read-
-     failure cases through a controlled transport; and
-   - assertions that every body is closed, no case reads beyond its bound,
-     declared oversize performs no read, and discarded details remain empty.
-3. Reuse existing controlled-transport and counting-reader helpers when they
-   are clear and package-local. Do not duplicate successful-response framing,
-   timeout, authentication, or endpoint matrices.
-
-### Verification
-
-```sh
-go test ./internal/llm -run 'TestOpenAICompatibleClient.*NonSuccess|TestProvider'
-go test ./internal/llm
-go test ./...
-```
-
-Stage 3 is complete when the built-in client emits the structured internal
-error for every non-2xx response and all prior internal identities remain
-green.
-
-**Status:** Complete.
-
-## Stage 4: Add the Public Error and Root Mapping Contract
-
-### Objective
-
-Translate only the built-in transport's structured error at the root facade,
-publish the immutable consumer API, and prove ordinary, prepared, and injected-
-client behavior.
-
-### Implementation
-
-1. Add `generation_error.go` in package `promptkit` with an immutable public
-   `GenerationError` whose four fields are unexported strings or integers. Add
-   one private constructor that accepts the four normalized scalar values. The
-   public error file must not import `internal/llm` or retain the internal error
-   or raw body; `errors.go` performs that adaptation at the facade boundary.
-2. Implement the four public accessors exactly as fixed above. Each returns
-   zero or empty on a nil receiver.
-3. Implement `Error()` with the fixed strings from this plan, `GoString()` by
-   returning `Error()`, and `Unwrap()` by returning `ErrLLMGenerate` even for a
-   nil receiver. Do not implement mutable fields, an exported constructor,
-   retry helpers, HTTP mapping, `fmt.Formatter`, or JSON methods.
-4. Write complete GoDoc covering:
-   - built-in-client and non-2xx scope;
-   - ordinary and prepared execution;
-   - `errors.Is` and pointer-target `errors.As` usage;
-   - immutable and caller-owned semantics;
-   - nil and zero behavior;
-   - lack of stable JSON;
-   - safe default formatting; and
-   - the fact that every provider accessor is untrusted and may contain
-     sensitive request or schema fragments.
-5. In `errors.go`, after the special capacity conversion and before generic
-   sentinel wrapping, use `errors.As` for a nonnil concrete
-   `*llm.ProviderHTTPError`. Convert it to `*GenerationError` and return that
-   public value directly. Do not parse error text or recognize an interface
-   that an injected client could accidentally satisfy.
-6. Preserve the existing generic `publicErrorFor` path for all other failures.
-   In particular, arbitrary injected-client errors remain wrapped with
-   `ErrLLMGenerate` and retain their original identity.
-7. Update public GoDoc in the same stage:
-   - the `ErrLLMGenerate` declaration points to `GenerationError` for built-in
-     non-2xx responses;
-   - `Engine.Run` and `Engine.RunPrepared` mention the typed error without
-     restating its accessors;
-   - `doc.go` distinguishes mutable `CapacityError` from immutable
-     `GenerationError`, lists both as lacking stable JSON, and calls out the
-     provider-detail trust boundary; and
-   - injected `LLMClient` GoDoc remains clear that arbitrary client errors are
-     preserved rather than translated.
-
-### Tests
-
-1. Add package-internal tests for `GenerationError` nil and zero receivers,
-   exact fixed formatting, and unwrapping. Do not expose a test-only public
-   constructor or turn the lack of stable JSON into a serialized-output
-   contract.
-2. Add a focused external-package contract test, preferably in
-   `generation_error_contract_test.go`, that obtains errors through a real
-   assembled engine with a controlled HTTP transport:
-   - an ordinary `Run` with a recognized envelope asserts a nil result,
-     `errors.Is(err, ErrLLMGenerate)`, pointer-target `errors.As`, all four
-     accessors, exact status-bearing formatting, and absence of distinctive
-     code/type/message markers from `%v`, `%+v`, and `%#v`;
-   - one `RunPrepared` case proves the same public type and status cross the
-     prepared boundary without repeating every parser field; and
-   - neither case contacts a live provider or uses a real credential.
-3. Extend the existing injected-client preservation owner with one assertion
-   that an arbitrary injected error does not become a `*GenerationError`, while
-   still matching both `ErrLLMGenerate` and the injected error.
-4. Keep detailed envelope, normalization, size, and body-ownership matrices in
-   `internal/llm`; root tests remain representative.
-
-### Verification
-
-```sh
-go test . -run 'TestGenerationError|TestBuiltInGenerationError|TestRunAddsLLMGenerate'
-go test ./internal/llm
-go test ./...
-```
-
-Stage 4 is complete when consumers can inspect built-in non-2xx details through
-the stable root contract and injected errors remain untouched.
-
-**Status:** Complete.
-
-## Stage 5: Update Canonical Documentation and Run Full Validation
-
-### Objective
-
-Make durable documentation match the implemented contract, remove the roadmap
-links that describe parsing as future work, and complete repository-wide
-validation.
-
-### Documentation
-
-1. Update `docs/integrations/openai-compatible-chat.md` as the canonical wire
-   owner. Replace the status-only paragraph with:
-   - the recognized top-level envelope and independent field types;
-   - strict single-document framing and unknown-field behavior;
-   - the exact 65,536-byte read policy and status-only fallbacks;
-   - exact normalization and field limits;
-   - response closure and no-overread behavior; and
-   - the prohibition on raw bodies, headers, endpoints, credentials, request
-     data, schemas, and generated content.
-2. Update `docs/internal/llm.md` with the internal `ProviderHTTPError`, bounded
-   reader and parser flow, retained `ErrUnexpectedStatus` identity, root
-   conversion boundary, and narrow test ownership. Remove its link that defers
-   parsing to the feature roadmap.
-3. Update `docs/consumers/pkg-promptkit.md` under `Handle Errors` with one short
-   `errors.As` example. Show status and deliberate message access, warn that all
-   provider fields are untrusted and potentially sensitive, leave retry and
-   presentation policy to the application, and link to `GenerationError`
-   GoDoc rather than duplicating its full contract.
-4. Update `docs/internal/overview.md` only enough to inventory implemented
-   responsibilities: the root facade owns typed capacity and generation error
-   mapping, and `internal/llm` owns bounded structured non-success response
-   decoding. Do not duplicate limits or accessor details there.
-5. Do not change `docs/policy/architecture.md`, `docs/formats.md`, backend
-   documentation, release notes, or the README unless implementation reveals a
-   concrete inaccurate statement. Their canonical topics do not own this
-   contract.
-
-### Final Validation
-
-Run the complete maintainer workflow from
-[`docs/development.md#maintainer-validation`](../development.md#maintainer-validation):
-
-```sh
-go test ./...
-go test -race ./...
-go vet ./...
-go build ./...
-go run ./examples/go-library/prepare
-go run ./examples/go-library/run
-```
-
-Also perform the documented Go-formatting, local Markdown-link, repository-
-hygiene, ignored-file, and credential scans. Review both example outputs and
-confirm that all commands remain deterministic, offline, and credential-free.
-
-Finally review the complete diff against the feature roadmap and confirm:
-
-- every built-in non-2xx response produces a status-bearing public type;
-- malformed and oversized bodies cannot erase status or leak partial content;
-- provider-derived strings appear only through deliberate accessors;
-- default and Go-syntax formatting are redacted;
-- successful, cancellation, capacity, validation, repair, and injected-client
-  behavior is unchanged;
-- no provider policy entered the use-case or domain layers; and
-- each exact contract has one canonical documentation and test owner.
-
-**Status:** Complete.
-
-## Open Questions
-
-None. The roadmap and this plan fix the public API, internal representation,
-wire envelope, normalization and bounds, status fallback, formatting,
-propagation, compatibility, documentation, and verification decisions required
-for implementation.

docs/roadmap/structured-generation-errors.md

@@ -1,260 +0,0 @@
-# Structured Generation Errors
-
-## Purpose
-
-Promptkit should give downstream applications actionable, machine-readable
-details when the built-in OpenAI-compatible client receives a non-success HTTP
-response. Today the client reports only the status code and discards the
-provider response body. This makes ordinary configuration failures, such as an
-unsupported strict JSON Schema keyword, unnecessarily difficult to diagnose.
-
-This feature supplies bounded facts about the provider response. It does not
-make retry, presentation, or logging decisions for consumers.
-
-## Target End State
-
-Every non-2xx response received by Promptkit's built-in OpenAI-compatible
-client becomes a public typed generation error. A consumer can use
-`errors.As` to obtain the HTTP status and any safely extracted provider fields,
-and `errors.Is` continues to match `ErrLLMGenerate`.
-
-The typed contract is available from both `Run` and `RunPrepared`. It is not
-produced during preparation, which performs no model request. Successful
-responses, transport failures before a response is received, cancellation,
-capacity failures, validation failures, and nil responses from injected model
-clients retain their existing categories and behavior.
-
-An unusable response body never hides the known HTTP status. Empty, malformed,
-unrecognized, unreadable, or oversized bodies therefore produce the same typed
-error with status-only detail rather than falling back to an unstructured
-error or becoming a malformed-success response.
-
-## Public Contract
-
-The root package exposes an immutable `GenerationError` type with unexported
-state and these read-only accessors:
-
-- `StatusCode() int` returns the received HTTP status code;
-- `ProviderCode() string` returns a normalized provider code, when present;
-- `ProviderType() string` returns a normalized provider error type, when
-  present; and
-- `ProviderMessage() string` returns the bounded normalized diagnostic message,
-  when present.
-
-The engine returns a `*GenerationError`, so the idiomatic inspection form is:
-
-```go
-var generationErr *promptkit.GenerationError
-if errors.As(err, &generationErr) {
-	status := generationErr.StatusCode()
-	message := generationErr.ProviderMessage()
-	_, _ = status, message
-}
-```
-
-There is no public constructor or mutation API. The type implements `error`,
-unwraps to `ErrLLMGenerate`, and provides safe ordinary and Go-syntax
-formatting. `Error()` and `GoString()` include the HTTP status but no provider-
-controlled code, type, or message. Consumers must use the accessors
-deliberately when they want provider details and must not classify failures by
-matching error text.
-
-The zero value and a nil `*GenerationError` receiver are safe: accessors return
-zero or empty values, formatting returns a generic redacted generation-failure
-description, and unwrapping still identifies `ErrLLMGenerate`. Engine-produced
-values always have the non-2xx status received from the provider. The type has
-no stable JSON representation.
-
-All provider-derived strings remain untrusted even after normalization. GoDoc
-must warn consumers that provider fields can contain sensitive request or
-schema fragments and must not be logged, displayed, or returned to another
-caller without an application-appropriate disclosure policy.
-
-## Recognized Provider Envelope
-
-Promptkit recognizes only the conventional OpenAI-compatible top-level error
-object:
-
-```json
-{
-  "error": {
-    "message": "diagnostic text",
-    "type": "invalid_request_error",
-    "code": "unsupported_parameter"
-  }
-}
-```
-
-The envelope must be one JSON document followed only by JSON whitespace. The
-top-level `error` value must be an object. Unknown top-level and error-object
-fields are ignored. The optional supported fields are interpreted
-independently:
-
-- `message` and `type` must be JSON strings;
-- `code` may be a JSON string or number and is exposed as normalized text;
-  numeric codes retain their validated JSON number text without floating-point
-  coercion; and
-- `null`, booleans, arrays, objects, or otherwise invalid values are treated as
-  absent for that field.
-
-An invalid optional field does not discard other valid supported fields. An
-absent `error` object, malformed or multiply framed JSON, or an object with no
-usable supported fields simply leaves all provider accessors empty while
-preserving the typed status error.
-
-Promptkit does not expose `param`, metadata objects, nested causes, headers, or
-provider-specific extensions in this feature.
-
-## Bounded Reading And Normalization
-
-Non-success bodies have a separate fixed limit of 64 KiB (65,536 bytes). This
-is intentionally much smaller than the successful completion-body limit while
-remaining large enough for useful schema diagnostics.
-
-- A declared `Content-Length` above the limit is rejected without reading the
-  body for detail extraction.
-- Otherwise Promptkit reads at most one byte beyond the limit so streamed,
-  chunked, and underreported bodies are bounded.
-- A body over the limit contributes no provider fields; Promptkit does not
-  parse or retain a prefix as though it were a complete envelope.
-- Read failures likewise discard provider fields while preserving the status.
-- The response body is closed on every outcome and is not drained beyond the
-  bounded read.
-
-Extracted strings are converted to valid UTF-8, trimmed, and made single-line:
-invalid UTF-8 is replaced, and runs of Unicode whitespace, control characters,
-and formatting controls are replaced with one ASCII space. Empty normalized
-values are treated as absent.
-
-Normalized provider codes and types are retained only when they contain at
-most 256 Unicode code points. Longer values are omitted rather than truncated
-so consumers never classify on a fabricated partial identifier. A provider
-message is limited to 4,096 Unicode code points; a longer normalized message is
-truncated at a code-point boundary with a visible ellipsis inside that limit.
-The raw response body and pre-normalized strings are never exposed or retained
-in the public error.
-
-## Error Propagation And Compatibility
-
-- Every built-in-client non-2xx response matches `ErrLLMGenerate` and supports
-  `errors.As` to `*GenerationError`, including status-only cases.
-- The internal model client retains its non-success-status identity for its
-  own package tests. The use-case layer remains provider-neutral and continues
-  to add only its generation category.
-- The root error boundary converts only the built-in transport's structured
-  status error. It does not parse arbitrary error text, inspect consumer error
-  fields, or fabricate HTTP details for an injected `LLMClient`.
-- Errors returned by injected clients remain in the chain exactly as today.
-  If an injected client deliberately returns an existing `*GenerationError`,
-  its identity may pass through ordinary wrapping, but Promptkit does not
-  construct or enrich one on that client's behalf.
-- Existing cancellation and deadline identities, capacity errors, validation
-  behavior, repair behavior, and successful response decoding remain
-  unchanged.
-- This is an additive public API. Existing consumers that use
-  `errors.Is(err, ErrLLMGenerate)` continue to work; consumers should not rely
-  on the previous rendered wording of non-success errors.
-
-## Architecture And Ownership
-
-The provider-envelope parser and bounded body reader belong in `internal/llm`,
-which owns the OpenAI-compatible transport. The internal transport error owns
-only normalized status facts and continues to match the package's existing
-non-success-status sentinel.
-
-The use-case package does not gain HTTP DTOs, status policy, or a provider-
-specific branch. Its existing wrapping carries the internal error to the root
-facade. The root error mapper recognizes the internal structured status error
-and constructs the public `GenerationError` without exposing an internal type
-or raw cause through public fields. No transport error is added to
-`internal/domain`.
-
-The public type and its exact Go semantics are owned by its declaration and
-GoDoc. The
-[OpenAI-compatible integration contract](../integrations/openai-compatible-chat.md)
-owns recognized wire shapes, limits, and observable response behavior. The
-[internal model-client document](../internal/llm.md) owns implementation flow,
-internal failure categories, and test ownership. Architecture policy does not
-need a new package or dependency rule for this feature.
-
-## Documentation End State
-
-Canonical documentation at the target state has these responsibilities:
-
-- the `GenerationError` declaration and GoDoc define the exact public methods,
-  formatting, unwrapping, zero-value behavior, and trust boundary;
-- `Engine.Run` and `Engine.RunPrepared` GoDoc identify the typed error without
-  duplicating its accessor contract;
-- the consumer guide includes one short `errors.As` example and links to the
-  public declaration;
-- the integration document replaces its status-only description with the
-  bounded envelope contract; and
-- the internal model-client document describes parsing, conversion ownership,
-  and narrow test owners.
-
-The architecture policy, framework format reference, and built-in backend
-catalog do not duplicate this API or wire contract.
-
-## Verification Expectations
-
-Verification protects each behavior at its narrowest stable owner:
-
-- internal model-client tests cover recognized string and numeric codes,
-  independent optional-field handling, unknown fields, empty and malformed
-  envelopes, single-document framing, read failures, declared and streamed
-  size boundaries, body closure, normalization, field limits, and absence of
-  raw provider content from rendered errors;
-- root error-boundary tests cover conversion to the immutable public type,
-  every accessor, `errors.Is`, `errors.As`, and safe `%v`, `%+v`, and `%#v`
-  formatting;
-- one representative ordinary run and one prepared run prove that the built-in
-  transport contract crosses the assembled engine boundary, without repeating
-  the complete parser matrix;
-- existing injected-client tests continue to prove preservation of consumer
-  error identity without fabricated provider details; and
-- all tests use controlled transports or local servers and never contact a
-  live or paid provider.
-
-Security limits and their exact boundaries are contractual enough to warrant
-literal boundary tests. Higher-level tests should remain representative and
-must not duplicate the internal transport matrix.
-
-## Acceptance Criteria
-
-- A consumer can distinguish an HTTP 400 from other generation failures and
-  deliberately obtain a bounded provider explanation when one is available.
-- The same typed error remains available through ordinary and prepared
-  execution and still satisfies `errors.Is(err, ErrLLMGenerate)`.
-- Default and Go-syntax error formatting cannot disclose any provider-derived
-  string or raw response content.
-- Empty, malformed, unreadable, unrecognized, and oversized bodies preserve a
-  typed status-only error.
-- No read, retained field, or formatted representation can exceed its stated
-  bound, and the body is closed on every outcome.
-- Existing success, cancellation, capacity, validation, repair, and injected-
-  client contracts remain unchanged.
-- Current-state documentation changes only when the implementation exists and
-  follows the repository's canonical ownership policy.
-
-## Non-Goals
-
-This feature does not add:
-
-- retryability classification, retry loops, backoff, failover, or routing;
-- parsing of success bodies as errors or changes to successful-response limits;
-- provider-specific envelope variants beyond the conventional top-level
-  `error` object;
-- response headers such as `Retry-After`, raw bodies, request data, endpoints,
-  credentials, schema documents, generated content, or provider metadata;
-- logging, telemetry, redaction policy for downstream applications, HTTP status
-  mapping for consumer servers, or user-facing presentation;
-- translation or enrichment of arbitrary injected-client errors; or
-- a new public package, public constructor, mutable error value, or transport
-  type in the domain model.
-
-## Open Questions
-
-None. The public type direction, accessor surface, formatting and error-chain
-behavior, envelope scope, normalization, safety limits, fallback behavior,
-layer ownership, compatibility boundaries, documentation ownership, and test
-boundaries are fixed by this roadmap.

engine.go

@@ -53,9 +53,9 @@ var (
 	// an execution profile or resolve its backend, except for the profile
 	// not-found case represented by ErrProfileNotFound.
 	ErrProfileLoad = errors.New("failed to load execution profile")
-	// ErrAPIKeyEnvMissing identifies an APIKeyEnv whose environment variable is
+	// ErrAPIKeyEnvMissing identifies an explicitly required APIKeyEnv whose
-	// unset or empty when no direct RunRequest.APIKey takes precedence. Such an
+	// environment variable is unset or empty after direct RunRequest.APIKey
-	// error also matches ErrInvalidRequest.
+	// precedence is applied. Such an error also matches ErrInvalidRequest.
 	ErrAPIKeyEnvMissing = errors.New("api_key_env points to an unset environment variable")
 	// ErrArtifactLoad identifies a failure to resolve an input artifact. Errors
 	// returned by an injected ArtifactReader remain available through errors.Is.
@@ -304,10 +304,12 @@ func WithFallbackProfileFS(fsys fs.FS, root string) Option {
 // WithProfiles configures in-memory profiles that take precedence over
 // ordinary configured, application fallback, and built-in profiles.
 //
-// NewEngine validates and copies every profile. IDs must be unique within one
+// NewEngine locally validates and copies every profile. IDs must be unique
-// call. An invalid profile, duplicate ID, or unsupported ExtraParams value
+// within one call. An invalid local definition, duplicate ID, or unsupported
-// makes construction fail with ErrInvalidConfig. Repeating WithProfiles
+// ExtraParams value makes construction fail with ErrInvalidConfig. A derived
-// replaces the complete earlier in-memory set rather than merging it.
+// profile's base reference and resolved target completeness are checked when it
+// is selected or inspected. Repeating WithProfiles replaces the complete
+// earlier in-memory set rather than merging it.
 func WithProfiles(profiles ...Profile) Option {
 	return optionFunc(func(options *engineOptions) error {
 		repo, err := newMemoryProfileRepository(profiles)
@@ -428,7 +430,7 @@ func NewEngine(cfg Config, opts ...Option) (*Engine, error) {
 	}
 
 	return &Engine{
-		runner: usecase.NewRunner(
+		runner: usecase.NewRunnerWithRepairer(
 			promptDefs,
 			profiles,
 			backendRegistry,
@@ -436,6 +438,7 @@ func NewEngine(cfg Config, opts ...Option) (*Engine, error) {
 			prompt.NewGoRenderer(),
 			llmClient,
 			validator,
+			usecase.NewDefaultOutputRepairer(llmClient),
 			capacityManager,
 		),
 	}, nil
@@ -458,7 +461,7 @@ func newProfileRepository(profileDir string, options engineOptions) profile.Repo
 		repository = profile.NewOverlayRepository(options.memoryProfiles, repository)
 	}
 
-	return repository
+	return profile.NewResolvingRepository(repository)
 }
 
 func fileSource(name string) (fs.FS, string, error) {
@@ -637,10 +640,12 @@ func (e *Engine) PrepareExecution(ctx context.Context, req RunRequest) (*Prepare
 // generated output.
 //
 // A content-validation failure is a successful run whose
-// RunResult.Validation has Status ValidationFailed. An inability to perform
+// RunResult.Validation has Status ValidationFailed. When its output contract
-// validation returns an error matching ErrValidation and no partial result.
+// has a positive repair budget, a failed eligible validation can make bounded
-// The public Engine does not perform output repair, so validation is
+// additional model calls and stops at the first valid candidate. Exhaustion
-// single-pass even when OutputContract.RepairAttempts is positive.
+// returns the final failed validation result with cumulative usage and actual
+// repair attempts. An inability to generate or validate returns an error and
+// no partial result.
 //
 // Run can return every error category documented by [Engine.Prepare], plus
 // ErrCapacityExceeded and ErrLLMGenerate. An engine admission rejection is
@@ -684,17 +689,17 @@ func (e *Engine) Run(ctx context.Context, req RunRequest) (*RunResult, error) {
 //
 // The supplied context governs this execution attempt independently of the
 // preparation context. It covers credential revalidation, admission,
-// generation, validation, and any internal repair. Result timing begins after
+// generation, validation, and any bounded output repair. Result timing begins
-// the claim and excludes preparation and consumer-held delay.
+// after the claim and excludes preparation and consumer-held delay.
 //
 // RunPrepared can return ErrInvalidRequest, ErrAPIKeyEnvMissing,
 // ErrCapacityExceeded, ErrLLMGenerate, or ErrValidation as applicable while
 // preserving documented collaborator and context identities. An engine
 // admission rejection is discoverable as [CapacityError] and still matches
 // ErrCapacityExceeded. A built-in OpenAI-compatible non-2xx response is
-// discoverable as [GenerationError]. A completed content-validation rejection
+// discoverable as [GenerationError]. A completed content-validation rejection,
-// is returned in RunResult, not as an operational error. An operational error
+// including repair exhaustion, is returned in RunResult, not as an operational
-// returns no partial RunResult.
+// error. An operational error returns no partial RunResult.
 func (e *Engine) RunPrepared(ctx context.Context, prepared *PreparedExecution) (*RunResult, error) {
 	if e == nil || e.runner == nil {
 		return nil, fmt.Errorf("%w: engine is nil", ErrInvalidConfig)

engine_test.go

@@ -977,37 +977,72 @@ func TestPrepareDirectAPIKeyBypassesMissingEnvWithoutLeakingOrHashing(t *testing
 	}
 }
 
-func TestMissingCredentialsFailClearlyWhenProfileRequiresAuth(t *testing.T) {
+func TestOptionalMissingCredentialsReachUpstream(t *testing.T) {
 	const missingEnv = "PROMPTKIT_PUBLIC_AUTH_MISSING"
+	const providerBody = `{"error":{"message":"authentication failed","type":"authentication_error","code":"invalid_api_key"}}`
 	t.Setenv(missingEnv, "")
 
-	profileDir := t.TempDir()
+	called := false
-	writePublicProfileFileWithAPIKeyEnv(t, profileDir, "requires-auth", "http://localhost:8000/v1", "test-model", missingEnv)
+	config := promptkit.Config{
-	engine, err := promptkit.NewEngine(promptkit.Config{
+		PromptDir: frameworkPromptDir,
-		PromptDir:  frameworkPromptDir,
+		SchemaDir: frameworkSchemaDir,
-		ProfileDir: profileDir,
+		HTTPClient: &http.Client{Transport: roundTripFunc(func(req *http.Request) (*http.Response, error) {
-		SchemaDir:  frameworkSchemaDir,
+			called = true
-	})
+			if values := req.Header.Values("Authorization"); len(values) != 0 {
+				t.Fatalf("Authorization values = %q, want absent", values)
+			}
+			return &http.Response{
+				StatusCode:    http.StatusUnauthorized,
+				ContentLength: int64(len(providerBody)),
+				Body:          io.NopCloser(strings.NewReader(providerBody)),
+			}, nil
+		})},
+	}
+	engine, err := promptkit.NewEngine(config,
+		promptkit.WithBackend(promptkit.Backend{
+			ID:        "optional-auth",
+			Endpoint:  "http://provider.test/v1",
+			APIKeyEnv: missingEnv,
+		}),
+		promptkit.WithProfiles(promptkit.Profile{
+			ID:        "optional-auth-profile",
+			BackendID: "optional-auth",
+			Model:     "test-model",
+		}),
+	)
 	if err != nil {
 		t.Fatalf("expected engine construction to succeed, got %v", err)
 	}
 
-	_, err = engine.Prepare(context.Background(), promptkit.RunRequest{
+	result, err := engine.Run(context.Background(), promptkit.RunRequest{
 		PromptID:  frameworkMarkdownSummaryPromptID,
-		ProfileID: "requires-auth",
+		ProfileID: "optional-auth-profile",
 		Inputs: map[string]promptkit.ArtifactRef{
 			"transcript": promptkit.Inline("Rin opens the gate."),
 			"glossary":   promptkit.Inline("gate: A guarded passage."),
 		},
 	})
-	if !errors.Is(err, promptkit.ErrInvalidRequest) {
+	if !called {
-		t.Fatalf("expected invalid request for missing credentials, got %v", err)
+		t.Fatal("optional missing credential did not reach upstream")
 	}
-	if !errors.Is(err, promptkit.ErrAPIKeyEnvMissing) {
+	if result != nil {
-		t.Fatalf("expected missing credential environment error, got %v", err)
+		t.Fatalf("result = %+v, want nil", result)
 	}
-	if err == nil || !strings.Contains(err.Error(), missingEnv) {
+	if errors.Is(err, promptkit.ErrInvalidRequest) || errors.Is(err, promptkit.ErrAPIKeyEnvMissing) {
-		t.Fatalf("expected missing env name in error, got %v", err)
+		t.Fatalf("error = %v, want upstream generation error without credential identities", err)
+	}
+	if !errors.Is(err, promptkit.ErrLLMGenerate) {
+		t.Fatalf("error = %v, want ErrLLMGenerate", err)
+	}
+	var generationErr *promptkit.GenerationError
+	if !errors.As(err, &generationErr) {
+		t.Fatalf("error = %v, want GenerationError", err)
+	}
+	if generationErr.StatusCode() != http.StatusUnauthorized ||
+		generationErr.ProviderType() != "authentication_error" ||
+		generationErr.ProviderCode() != "invalid_api_key" ||
+		generationErr.ProviderMessage() != "authentication failed" {
+		t.Fatalf("GenerationError = %+v, want structured upstream authentication failure", generationErr)
 	}
 }
 
@@ -1983,6 +2018,25 @@ func TestWithProfilesRejectsDuplicateIDs(t *testing.T) {
 	}
 }
 
+func TestWithProfilesAcceptsDerivedDefinitionWithoutTargetFields(t *testing.T) {
+	_, err := promptkit.NewEngine(promptkit.Config{PromptDir: frameworkPromptDir},
+		promptkit.WithProfiles(promptkit.Profile{
+			ID:            " derived-profile ",
+			BaseProfileID: " base-profile ",
+		}),
+	)
+	if err != nil {
+		t.Fatalf("derived profile should be accepted during construction: %v", err)
+	}
+
+	_, err = promptkit.NewEngine(promptkit.Config{PromptDir: frameworkPromptDir},
+		promptkit.WithProfiles(promptkit.Profile{ID: "standalone-profile"}),
+	)
+	if !errors.Is(err, promptkit.ErrInvalidConfig) {
+		t.Fatalf("standalone incomplete profile error = %v, want ErrInvalidConfig", err)
+	}
+}
+
 func TestWithProfilesRejectsInvalidExecutionSettings(t *testing.T) {
 	type testCase struct {
 		name    string
@@ -2135,6 +2189,7 @@ func TestOpenAICompatibleProfileMapsEveryField(t *testing.T) {
 	extraParams := map[string]any{"provider_option": "distinct-extra-params"}
 	got := promptkit.OpenAICompatibleProfile(promptkit.OpenAICompatibleProfileConfig{
 		ID:              "distinct-id",
+		BaseProfileID:   "distinct-base",
 		BackendID:       "distinct-backend",
 		Endpoint:        "https://distinct.example/v1",
 		Model:           "distinct-model",
@@ -2149,6 +2204,7 @@ func TestOpenAICompatibleProfileMapsEveryField(t *testing.T) {
 	})
 	want := promptkit.Profile{
 		ID:              "distinct-id",
+		BaseProfileID:   "distinct-base",
 		BackendID:       "distinct-backend",
 		Endpoint:        "https://distinct.example/v1",
 		Model:           "distinct-model",
@@ -3430,9 +3486,10 @@ extra_params:
 }
 
 type fakeLLMClient struct {
-	response *promptkit.GenerateResponse
+	response  *promptkit.GenerateResponse
-	err      error
+	responses []*promptkit.GenerateResponse
-	requests []promptkit.GenerateRequest
+	err       error
+	requests  []promptkit.GenerateRequest
 }
 
 type recordingArtifactReader struct {
@@ -3608,5 +3665,12 @@ func (f *fakeLLMClient) Generate(_ context.Context, req promptkit.GenerateReques
 	if f.err != nil {
 		return nil, f.err
 	}
+	if len(f.responses) > 0 {
+		index := len(f.requests) - 1
+		if index >= len(f.responses) {
+			return nil, fmt.Errorf("no response configured for generation %d", index+1)
+		}
+		return f.responses[index], nil
+	}
 	return f.response, nil
 }

errors.go

@@ -21,16 +21,20 @@ func mapPublicError(err error) error {
 		strings.TrimSpace(internalCapacityError.BackendID) != "" {
 		return &CapacityError{BackendID: internalCapacityError.BackendID}
 	}
+	publicErr := publicErrorFor(err)
 	var providerHTTPError *llm.ProviderHTTPError
 	if errors.As(err, &providerHTTPError) && providerHTTPError != nil {
-		return newGenerationError(
+		generationErr := newGenerationError(
 			providerHTTPError.StatusCode(),
 			providerHTTPError.ProviderCode(),
 			providerHTTPError.ProviderType(),
 			providerHTTPError.ProviderMessage(),
 		)
+		if publicErr != nil && !errors.Is(publicErr, ErrLLMGenerate) {
+			return fmt.Errorf("%w: %w", publicErr, generationErr)
+		}
+		return generationErr
 	}
-	publicErr := publicErrorFor(err)
 	if publicErr == nil {
 		return err
 	}

errors_internal_test.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"testing"
 
+	"gitea.maximumdirect.net/eric/promptkit/internal/llm"
 	"gitea.maximumdirect.net/eric/promptkit/internal/usecase"
 )
 
@@ -48,3 +49,27 @@ func TestMapPublicErrorTranslatesCapacityError(t *testing.T) {
 		t.Fatalf("mapped backend ID changed with source error: %q", publicErr.BackendID)
 	}
 }
+
+func TestMapPublicErrorPreservesValidationAroundGenerationError(t *testing.T) {
+	internalErr := fmt.Errorf(
+		"%w: %w",
+		usecase.ErrValidation,
+		&llm.ProviderHTTPError{},
+	)
+
+	err := mapPublicError(internalErr)
+	if !errors.Is(err, ErrValidation) {
+		t.Fatalf("mapped error=%v, want ErrValidation", err)
+	}
+	if !errors.Is(err, ErrLLMGenerate) {
+		t.Fatalf("mapped error=%v, want ErrLLMGenerate", err)
+	}
+	var generationErr *GenerationError
+	if !errors.As(err, &generationErr) || generationErr == nil {
+		t.Fatalf("mapped error=%v, want GenerationError", err)
+	}
+	var leakedInternalErr *llm.ProviderHTTPError
+	if errors.As(err, &leakedInternalErr) {
+		t.Fatalf("mapped error exposes internal ProviderHTTPError: %v", err)
+	}
+}

generation_error_contract_test.go

@@ -39,6 +39,44 @@ func TestBuiltInGenerationError(t *testing.T) {
 	assertGenerationError(t, err, http.StatusServiceUnavailable, "", "", "")
 }
 
+func TestBuiltInRepairGenerationError(t *testing.T) {
+	const (
+		codeMarker    = "repair-code-marker"
+		typeMarker    = "repair-type-marker"
+		messageMarker = "repair-message-marker"
+	)
+	calls := 0
+	config := contractConfig(frameworkSchemaDir)
+	config.HTTPClient = &http.Client{Transport: roundTripFunc(func(*http.Request) (*http.Response, error) {
+		calls++
+		if calls == 1 {
+			body := `{"choices":[{"message":{"content":"not-json"}}]}`
+			return &http.Response{StatusCode: http.StatusOK, ContentLength: int64(len(body)), Body: io.NopCloser(strings.NewReader(body))}, nil
+		}
+		body := `{"error":{"code":"` + codeMarker + `","type":"` + typeMarker + `","message":"` + messageMarker + `"}}`
+		return &http.Response{StatusCode: http.StatusUnprocessableEntity, ContentLength: int64(len(body)), Body: io.NopCloser(strings.NewReader(body))}, nil
+	})}
+	engine, err := promptkit.NewEngine(config)
+	if err != nil {
+		t.Fatalf("NewEngine: %v", err)
+	}
+	req := generationErrorRunRequest()
+	req.Validation = &promptkit.OutputContract{
+		Format:         promptkit.FormatJSON,
+		ValidationMode: promptkit.ValidationJSON,
+		RepairAttempts: 1,
+	}
+
+	result, err := engine.Run(context.Background(), req)
+	if result != nil {
+		t.Fatalf("Run result = %#v, want nil", result)
+	}
+	if calls != 2 {
+		t.Fatalf("provider calls = %d, want 2", calls)
+	}
+	assertGenerationError(t, err, http.StatusUnprocessableEntity, codeMarker, typeMarker, messageMarker)
+}
+
 func assertGenerationError(t *testing.T, err error, statusCode int, code, providerType, message string) {
 	t.Helper()
 

internal/domain/domain.go

@@ -192,6 +192,7 @@ type BackendCapacityPolicy struct {
 // ExecutionProfile describes how and where to execute a model.
 type ExecutionProfile struct {
 	ID              string         `yaml:"id"`
+	BaseProfileID   string         `yaml:"base_profile"`
 	BackendID       string         `yaml:"backend"`
 	Endpoint        string         `yaml:"endpoint"`
 	Model           string         `yaml:"model"`

internal/domain/output_contract.go

@@ -6,6 +6,8 @@ import (
 	"strings"
 )
 
+const maxOutputRepairAttempts = 3
+
 // ValidateOutputContract validates source-neutral output-contract invariants.
 func ValidateOutputContract(contract OutputContract) error {
 	switch contract.Format {
@@ -26,5 +28,11 @@ func ValidateOutputContract(contract OutputContract) error {
 	if contract.RepairAttempts < 0 {
 		return errors.New("repair_attempts must be greater than or equal to 0")
 	}
+	if contract.RepairAttempts > maxOutputRepairAttempts {
+		return fmt.Errorf("repair_attempts must be less than or equal to %d", maxOutputRepairAttempts)
+	}
+	if contract.ValidationMode == ValidationNone && contract.RepairAttempts > 0 {
+		return errors.New("repair_attempts requires basic, json, or json_schema validation")
+	}
 	return nil
 }

internal/domain/output_contract_test.go

@@ -30,9 +30,28 @@ func TestValidateOutputContract(t *testing.T) {
 		}},
 		{name: "empty validation mode", change: func(c *OutputContract) { c.ValidationMode = "" }, wantErr: "validation mode"},
 		{name: "unsupported validation mode", change: func(c *OutputContract) { c.ValidationMode = ValidationMode("unknown") }, wantErr: "validation mode"},
-		{name: "negative repair attempts", change: func(c *OutputContract) { c.RepairAttempts = -1 }, wantErr: "repair_attempts"},
+		{name: "negative repair attempts", change: func(c *OutputContract) {
+			c.ValidationMode = ValidationBasic
+			c.RepairAttempts = -1
+		}, wantErr: "repair_attempts"},
 		{name: "zero repair attempts", change: func(c *OutputContract) { c.RepairAttempts = 0 }},
-		{name: "positive repair attempts", change: func(c *OutputContract) { c.RepairAttempts = 1 }},
+		{name: "one repair attempt", change: func(c *OutputContract) {
+			c.ValidationMode = ValidationBasic
+			c.RepairAttempts = 1
+		}},
+		{name: "maximum repair attempts", change: func(c *OutputContract) {
+			c.ValidationMode = ValidationJSON
+			c.RepairAttempts = 3
+		}},
+		{name: "too many repair attempts", change: func(c *OutputContract) {
+			c.ValidationMode = ValidationJSONSchema
+			c.SchemaPath = "schema.json"
+			c.RepairAttempts = 4
+		}, wantErr: "repair_attempts"},
+		{name: "none validation with repair attempts", change: func(c *OutputContract) {
+			c.ValidationMode = ValidationNone
+			c.RepairAttempts = 1
+		}, wantErr: "repair_attempts"},
 		{name: "json schema empty path", change: func(c *OutputContract) {
 			c.ValidationMode = ValidationJSONSchema
 			c.SchemaPath = ""

internal/llm/openai_compatible_client.go

@@ -133,13 +133,18 @@ func (c *OpenAICompatibleClient) Generate(ctx context.Context, req domain.Genera
 		return nil, fmt.Errorf("%w: failed to create request: %v", ErrRequestFailed, err)
 	}
 	httpReq.Header.Set("Content-Type", "application/json")
-	if apiKey := strings.TrimSpace(req.Target.APIKey); apiKey != "" {
+	apiKey := strings.TrimSpace(req.Target.APIKey)
-		httpReq.Header.Set("Authorization", "Bearer "+apiKey)
+	envName := strings.TrimSpace(req.Target.APIKeyEnv)
-	} else if envName := strings.TrimSpace(req.Target.APIKeyEnv); envName != "" {
+	if apiKey == "" && envName != "" {
-		apiKey := strings.TrimSpace(os.Getenv(envName))
+		apiKey = strings.TrimSpace(os.Getenv(envName))
-		if apiKey == "" {
+	}
+	if apiKey == "" && req.Target.APIKeyRequired {
+		if envName != "" {
 			return nil, fmt.Errorf("%w: api key environment variable %q is not set", ErrInvalidRequest, envName)
 		}
+		return nil, fmt.Errorf("%w: api key is required", ErrInvalidRequest)
+	}
+	if apiKey != "" {
 		httpReq.Header.Set("Authorization", "Bearer "+apiKey)
 	}
 
@@ -174,12 +179,12 @@ func (c *OpenAICompatibleClient) Generate(ctx context.Context, req domain.Genera
 		return nil, fmt.Errorf("%w: no choices returned", ErrMalformedResponse)
 	}
 	content := wireResp.Choices[0].Message.Content
-	if content == "" {
+	if content == nil {
-		return nil, fmt.Errorf("%w: first choice has empty message content", ErrMalformedResponse)
+		return nil, fmt.Errorf("%w: first choice has missing message content", ErrMalformedResponse)
 	}
 
 	return &domain.GenerateResponse{
-		Content: content,
+		Content: *content,
 		Usage: domain.TokenUsage{
 			PromptTokens:     wireResp.Usage.PromptTokens,
 			CompletionTokens: wireResp.Usage.CompletionTokens,
@@ -374,8 +379,8 @@ type openAICacheControl struct {
 }
 
 type openAIChatResponseMessage struct {
-	Role    string `json:"role"`
+	Role    string  `json:"role"`
-	Content string `json:"content"`
+	Content *string `json:"content"`
 }
 
 type openAIChatResponse struct {

internal/llm/openai_compatible_client_test.go

@@ -501,36 +501,61 @@ func checkCompleteRequestAndResponseMapping(t *testing.T) {
 
 func TestOpenAICompatibleClientAuthentication(t *testing.T) {
 	tests := []struct {
-		name          string
+		name              string
-		configureEnv  func(*testing.T)
+		configureEnv      func(*testing.T)
-		target        domain.ExecutionTarget
+		target            domain.ExecutionTarget
-		wantAuth      string
+		wantAuthorization string
-		wantErr       error
+		wantError         error
-		wantCallCount int
+		wantCallCount     int
 	}{
 		{
 			name: "direct key takes precedence over environment",
 			configureEnv: func(t *testing.T) {
-				t.Setenv("PROMPTKIT_TEST_API_KEY", "env-key")
+				t.Setenv("PROMPTKIT_TEST_API_KEY", " env-key ")
 			},
 			target: domain.ExecutionTarget{
 				APIKeyEnv: "PROMPTKIT_TEST_API_KEY",
-				APIKey:    "direct-llm-key",
+				APIKey:    " direct-llm-key ",
 			},
-			wantAuth:      "Bearer direct-llm-key",
+			wantAuthorization: "Bearer direct-llm-key",
-			wantCallCount: 1,
+			wantCallCount:     1,
+		},
+		{
+			name: "environment key supplies authorization",
+			configureEnv: func(t *testing.T) {
+				t.Setenv("PROMPTKIT_TEST_API_KEY", " env-key ")
+			},
+			target:            domain.ExecutionTarget{APIKeyEnv: "PROMPTKIT_TEST_API_KEY"},
+			wantAuthorization: "Bearer env-key",
+			wantCallCount:     1,
 		},
 		{
 			name:          "no key omits authorization",
 			wantCallCount: 1,
 		},
 		{
-			name: "missing environment key fails before transport",
+			name: "optional missing environment omits authorization",
 			configureEnv: func(t *testing.T) {
 				t.Setenv("PROMPTKIT_MISSING_KEY", "")
 			},
-			target:  domain.ExecutionTarget{APIKeyEnv: "PROMPTKIT_MISSING_KEY"},
+			target:        domain.ExecutionTarget{APIKeyEnv: "PROMPTKIT_MISSING_KEY"},
-			wantErr: ErrInvalidRequest,
+			wantCallCount: 1,
+		},
+		{
+			name: "required missing environment fails before transport",
+			configureEnv: func(t *testing.T) {
+				t.Setenv("PROMPTKIT_MISSING_KEY", "")
+			},
+			target: domain.ExecutionTarget{
+				APIKeyEnv:      "PROMPTKIT_MISSING_KEY",
+				APIKeyRequired: true,
+			},
+			wantError: ErrInvalidRequest,
+		},
+		{
+			name:      "required target without source fails before transport",
+			target:    domain.ExecutionTarget{APIKeyRequired: true},
+			wantError: ErrInvalidRequest,
 		},
 	}
 
@@ -545,9 +570,9 @@ func TestOpenAICompatibleClientAuthentication(t *testing.T) {
 			request.Target = tc.target
 
 			_, err := client.Generate(context.Background(), request)
-			if tc.wantErr != nil {
+			if tc.wantError != nil {
-				if !errors.Is(err, tc.wantErr) {
+				if !errors.Is(err, tc.wantError) {
-					t.Fatalf("error = %v, want %v", err, tc.wantErr)
+					t.Fatalf("error = %v, want %v", err, tc.wantError)
 				}
 			} else if err != nil {
 				t.Fatalf("generate: %v", err)
@@ -556,8 +581,13 @@ func TestOpenAICompatibleClientAuthentication(t *testing.T) {
 				t.Fatalf("provider calls = %d, want %d", got, tc.wantCallCount)
 			}
 			if tc.wantCallCount == 1 {
-				if got := provider.lastRequest(t).header.Get("Authorization"); got != tc.wantAuth {
+				values := provider.lastRequest(t).header.Values("Authorization")
-					t.Fatalf("Authorization = %q, want %q", got, tc.wantAuth)
+				if tc.wantAuthorization == "" {
+					if len(values) != 0 {
+						t.Fatalf("Authorization values = %q, want absent", values)
+					}
+				} else if len(values) != 1 || values[0] != tc.wantAuthorization {
+					t.Fatalf("Authorization values = %q, want [%q]", values, tc.wantAuthorization)
 				}
 			}
 		})
@@ -735,6 +765,7 @@ func TestOpenAICompatibleClientResponseFraming(t *testing.T) {
 		run  func(*testing.T)
 	}{
 		{name: "usage mapping", run: checkCacheUsageMapping},
+		{name: "content presence", run: checkContentPresence},
 		{name: "common response failures", run: checkCommonResponseFailures},
 		{name: "successful response byte boundary", run: checkSuccessfulResponseByteBoundary},
 		{name: "continuing oversized response", run: checkContinuingOversizedResponse},
@@ -746,6 +777,53 @@ func TestOpenAICompatibleClientResponseFraming(t *testing.T) {
 	}
 }
 
+func checkContentPresence(t *testing.T) {
+	tests := []struct {
+		name    string
+		content string
+	}{
+		{name: "explicit empty string", content: ""},
+		{name: "whitespace string", content: " \n\t "},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			provider := newRecordingProvider(t)
+			provider.respond(http.StatusOK, `{
+  "choices": [{"message": {"content": `+strconv.Quote(tc.content)+`}}],
+  "usage": {
+    "prompt_tokens": 10,
+    "completion_tokens": 20,
+    "total_tokens": 30,
+    "prompt_tokens_details": {"cached_tokens": 4},
+    "cache_write_tokens": 5
+  }
+}`)
+			client := newProviderClient(t, provider, OpenAICompatibleConfig{Model: "model"})
+
+			response, err := client.Generate(context.Background(), ordinaryGenerateRequest())
+			if err != nil {
+				t.Fatalf("generate: %v", err)
+			}
+			if response == nil {
+				t.Fatal("expected response")
+			}
+			if response.Content != tc.content {
+				t.Fatalf("content = %q, want %q", response.Content, tc.content)
+			}
+			if response.Usage != (domain.TokenUsage{
+				PromptTokens:     10,
+				CompletionTokens: 20,
+				TotalTokens:      30,
+				CachedTokens:     4,
+				CacheWriteTokens: 5,
+			}) {
+				t.Fatalf("usage = %+v", response.Usage)
+			}
+		})
+	}
+}
+
 func checkCacheUsageMapping(t *testing.T) {
 	provider := newRecordingProvider(t)
 	provider.respond(http.StatusOK, `{
@@ -1099,6 +1177,9 @@ func checkCommonResponseFailures(t *testing.T) {
 		},
 		{name: "invalid JSON", statusCode: http.StatusOK, body: `{not valid json`, wantErr: ErrMalformedResponse},
 		{name: "missing choices", statusCode: http.StatusOK, body: `{"choices": []}`, wantErr: ErrMalformedResponse},
+		{name: "missing content", statusCode: http.StatusOK, body: `{"choices": [{"message": {}}]}`, wantErr: ErrMalformedResponse},
+		{name: "null content", statusCode: http.StatusOK, body: `{"choices": [{"message": {"content": null}}]}`, wantErr: ErrMalformedResponse},
+		{name: "non-string content", statusCode: http.StatusOK, body: `{"choices": [{"message": {"content": 1}}]}`, wantErr: ErrMalformedResponse},
 	}
 
 	for _, tc := range tests {

internal/profile/definition.go

@@ -0,0 +1,47 @@
+package profile
+
+import (
+	"errors"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
+)
+
+// NormalizeAndValidateDefinition normalizes and validates one source-local
+// profile definition without resolving a base profile.
+func NormalizeAndValidateDefinition(profile *domain.ExecutionProfile) error {
+	if profile == nil {
+		return errors.New("profile is required")
+	}
+
+	profile.ID = strings.TrimSpace(profile.ID)
+	profile.BaseProfileID = strings.TrimSpace(profile.BaseProfileID)
+	profile.BackendID = strings.TrimSpace(profile.BackendID)
+	profile.Endpoint = strings.TrimSpace(profile.Endpoint)
+
+	if profile.ID == "" {
+		return errors.New("id is required")
+	}
+	if profile.Endpoint != "" {
+		endpoint, err := domain.NormalizeOpenAICompatibleBaseEndpoint(profile.Endpoint)
+		if err != nil {
+			return err
+		}
+		profile.Endpoint = endpoint
+	}
+	if profile.BaseProfileID == "" {
+		if profile.BackendID == "" && profile.Endpoint == "" {
+			return errors.New("backend or endpoint is required")
+		}
+		if strings.TrimSpace(profile.Model) == "" {
+			return errors.New("model is required")
+		}
+	}
+
+	return domain.ValidateExecutionTargetSettings(domain.ExecutionTarget{
+		Temperature:    profile.Temperature,
+		MaxTokens:      profile.MaxTokens,
+		TopP:           profile.TopP,
+		TimeoutSeconds: profile.TimeoutSeconds,
+	})
+}

internal/profile/filesystem_repository.go

@@ -127,12 +127,11 @@ func loadProfile(ctx context.Context, fsys fs.FS, root string, id string) (*doma
 		if prof.ID != id {
 			continue
 		}
-		prof.BackendID = strings.TrimSpace(prof.BackendID)
 		prof.ExtraParams, err = jsonvalue.CopyMap(prof.ExtraParams)
 		if err != nil {
 			return nil, fmt.Errorf("%w: %s: %v", ErrInvalidProfile, relPath, err)
 		}
-		if err := normalizeAndValidateProfile(prof); err != nil {
+		if err := NormalizeAndValidateDefinition(prof); err != nil {
 			if errors.Is(err, ErrRawAPIKeyNotAllowed) {
 				return nil, fmt.Errorf("%w: %s", err, relPath)
 			}
@@ -255,30 +254,3 @@ func requireYAMLStreamEnd(decoder *yaml.Decoder) error {
 	}
 	return errors.New("profile file must contain exactly one YAML document")
 }
-
-func normalizeAndValidateProfile(p *domain.ExecutionProfile) error {
-	if strings.TrimSpace(p.ID) == "" {
-		return errors.New("id is required")
-	}
-	p.Endpoint = strings.TrimSpace(p.Endpoint)
-	if strings.TrimSpace(p.BackendID) == "" && p.Endpoint == "" {
-		return errors.New("backend or endpoint is required")
-	}
-	if p.Endpoint != "" {
-		endpoint, err := domain.NormalizeOpenAICompatibleBaseEndpoint(p.Endpoint)
-		if err != nil {
-			return err
-		}
-		p.Endpoint = endpoint
-	}
-	if strings.TrimSpace(p.Model) == "" {
-		return errors.New("model is required")
-	}
-
-	return domain.ValidateExecutionTargetSettings(domain.ExecutionTarget{
-		Temperature:    p.Temperature,
-		MaxTokens:      p.MaxTokens,
-		TopP:           p.TopP,
-		TimeoutSeconds: p.TimeoutSeconds,
-	})
-}

internal/profile/repository_test.go

@@ -858,6 +858,107 @@ top_p: .inf
 	})
 }
 
+func TestProfileRepositoriesValidateDerivedDefinitions(t *testing.T) {
+	tests := []struct {
+		name        string
+		files       map[string]string
+		wantError   error
+		wantBaseID  string
+		wantProfile bool
+	}{
+		{
+			name: "alias is locally valid and normalizes base id",
+			files: map[string]string{"alias.yaml": `
+id: selected-profile
+base_profile: "  base-profile  "
+`},
+			wantBaseID:  "base-profile",
+			wantProfile: true,
+		},
+		{
+			name: "derived endpoint remains valid",
+			files: map[string]string{"invalid.yaml": `
+id: selected-profile
+base_profile: base-profile
+endpoint: /v1
+`},
+			wantError: ErrInvalidProfile,
+		},
+		{
+			name: "derived settings remain valid",
+			files: map[string]string{"invalid.yaml": `
+id: selected-profile
+base_profile: base-profile
+top_p: 1.1
+`},
+			wantError: ErrInvalidProfile,
+		},
+		{
+			name: "derived extra params remain valid",
+			files: map[string]string{"invalid.yaml": `
+id: selected-profile
+base_profile: base-profile
+extra_params:
+  timestamp: 2026-08-11T12:34:56Z
+`},
+			wantError: ErrInvalidProfile,
+		},
+		{
+			name: "derived raw key remains prohibited",
+			files: map[string]string{"invalid.yaml": `
+id: selected-profile
+base_profile: base-profile
+api_key: secret
+`},
+			wantError: ErrRawAPIKeyNotAllowed,
+		},
+		{
+			name: "derived duplicate id remains invalid",
+			files: map[string]string{
+				"first.yaml":  "id: selected-profile\nbase_profile: first-base\n",
+				"second.yaml": "id: selected-profile\nbase_profile: second-base\n",
+			},
+			wantError: ErrInvalidProfile,
+		},
+		{
+			name: "derived extra document remains invalid",
+			files: map[string]string{"invalid.yaml": `
+id: selected-profile
+base_profile: base-profile
+---
+id: other
+`},
+			wantError: ErrInvalidYAML,
+		},
+		{
+			name:      "standalone profile remains complete",
+			files:     map[string]string{"invalid.yaml": "id: selected-profile\n"},
+			wantError: ErrInvalidProfile,
+		},
+	}
+
+	for _, source := range profileRepositorySources() {
+		for _, tc := range tests {
+			t.Run(source.name+"/"+tc.name, func(t *testing.T) {
+				repo := source.newRepository(t, tc.files)
+				got, err := repo.GetProfile(context.Background(), "selected-profile")
+				if tc.wantError != nil {
+					if !errors.Is(err, tc.wantError) {
+						t.Fatalf("error = %v, want %v", err, tc.wantError)
+					}
+					return
+				}
+				if err != nil || !tc.wantProfile {
+					t.Fatalf("profile = %+v, error = %v, want valid derived definition", got, err)
+				}
+				if got.BaseProfileID != tc.wantBaseID {
+					t.Fatalf("BaseProfileID = %q, want %q", got.BaseProfileID, tc.wantBaseID)
+				}
+			})
+		}
+	}
+}
+
 func TestOverlayRepository(t *testing.T) {
 	ctx := context.Background()
 	primaryProfile := &domain.ExecutionProfile{ID: "shared", Endpoint: "http://primary", Model: "primary"}

internal/profile/resolving_repository.go

@@ -0,0 +1,160 @@
+package profile
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
+	"gitea.maximumdirect.net/eric/promptkit/internal/jsonvalue"
+)
+
+const maximumProfileChainLength = 32
+
+type resolvingRepository struct {
+	source Repository
+}
+
+// NewResolvingRepository resolves inherited profile definitions from source.
+func NewResolvingRepository(source Repository) Repository {
+	return &resolvingRepository{source: source}
+}
+
+func (r *resolvingRepository) GetProfile(ctx context.Context, id string) (*domain.ExecutionProfile, error) {
+	if r == nil || r.source == nil {
+		return nil, fmt.Errorf("%w: profile repository is required", ErrInvalidProfile)
+	}
+	requestedID := strings.TrimSpace(id)
+	if requestedID == "" {
+		return nil, fmt.Errorf("%w: profile id is required", ErrInvalidProfile)
+	}
+	if err := ctx.Err(); err != nil {
+		return nil, err
+	}
+
+	profile, err := r.getRawProfile(ctx, requestedID)
+	if err != nil {
+		return nil, err
+	}
+	if profile == nil {
+		return nil, fmt.Errorf("%w: selected profile %q is nil", ErrInvalidProfile, requestedID)
+	}
+
+	chain := []*domain.ExecutionProfile{profile}
+	chainIDs := []string{requestedID}
+	visited := map[string]struct{}{requestedID: {}}
+	current := profile
+
+	for {
+		baseID := strings.TrimSpace(current.BaseProfileID)
+		if baseID == "" {
+			break
+		}
+		if err := ctx.Err(); err != nil {
+			return nil, err
+		}
+		if _, seen := visited[baseID]; seen {
+			return nil, fmt.Errorf("%w: profile inheritance cycle %s", ErrInvalidProfile, joinProfileChain(chainIDs, baseID))
+		}
+		if len(chain) >= maximumProfileChainLength {
+			return nil, fmt.Errorf("%w: profile inheritance chain exceeds %d profiles: %s", ErrInvalidProfile, maximumProfileChainLength, joinProfileChain(chainIDs, baseID))
+		}
+
+		base, err := r.getRawProfile(ctx, baseID)
+		if err != nil {
+			if errors.Is(err, ErrProfileNotFound) {
+				return nil, fmt.Errorf("%w: base profile %q is missing in chain %s", ErrInvalidProfile, baseID, joinProfileChain(chainIDs, baseID))
+			}
+			return nil, fmt.Errorf("%w: failed to load base profile %q in chain %s: %w", ErrInvalidProfile, baseID, joinProfileChain(chainIDs, baseID), err)
+		}
+		if base == nil {
+			return nil, fmt.Errorf("%w: base profile %q is nil in chain %s", ErrInvalidProfile, baseID, joinProfileChain(chainIDs, baseID))
+		}
+
+		chain = append(chain, base)
+		chainIDs = append(chainIDs, baseID)
+		visited[baseID] = struct{}{}
+		current = base
+	}
+
+	resolved, err := mergeProfileChain(chain)
+	if err != nil {
+		return nil, fmt.Errorf("%w: resolved profile chain %s: %w", ErrInvalidProfile, strings.Join(chainIDs, " -> "), err)
+	}
+	if err := validateResolvedProfile(resolved); err != nil {
+		return nil, fmt.Errorf("%w: resolved profile chain %s: %w", ErrInvalidProfile, strings.Join(chainIDs, " -> "), err)
+	}
+	return resolved, nil
+}
+
+func (r *resolvingRepository) getRawProfile(ctx context.Context, id string) (*domain.ExecutionProfile, error) {
+	profile, err := r.source.GetProfile(ctx, id)
+	if err != nil {
+		return nil, err
+	}
+	if err := ctx.Err(); err != nil {
+		return nil, err
+	}
+	return profile, nil
+}
+
+func joinProfileChain(chain []string, next string) string {
+	return strings.Join(append(append([]string(nil), chain...), next), " -> ")
+}
+
+func mergeProfileChain(chain []*domain.ExecutionProfile) (*domain.ExecutionProfile, error) {
+	resolved := &domain.ExecutionProfile{ID: chain[0].ID}
+	for index := len(chain) - 1; index >= 0; index-- {
+		definition := chain[index]
+		if strings.TrimSpace(definition.BackendID) != "" {
+			resolved.BackendID = definition.BackendID
+		}
+		if strings.TrimSpace(definition.Endpoint) != "" {
+			resolved.Endpoint = definition.Endpoint
+		}
+		if strings.TrimSpace(definition.Model) != "" {
+			resolved.Model = definition.Model
+		}
+		if definition.Temperature != 0 {
+			resolved.Temperature = definition.Temperature
+		}
+		if definition.MaxTokens != 0 {
+			resolved.MaxTokens = definition.MaxTokens
+		}
+		if definition.TopP != 0 {
+			resolved.TopP = definition.TopP
+		}
+		if definition.TimeoutSeconds != 0 {
+			resolved.TimeoutSeconds = definition.TimeoutSeconds
+		}
+		if strings.TrimSpace(definition.ServiceTier) != "" {
+			resolved.ServiceTier = definition.ServiceTier
+		}
+		if strings.TrimSpace(definition.ReasoningEffort) != "" {
+			resolved.ReasoningEffort = definition.ReasoningEffort
+		}
+		if strings.TrimSpace(definition.APIKeyEnv) != "" {
+			resolved.APIKeyEnv = definition.APIKeyEnv
+		}
+		resolved.APIKeyRequired = resolved.APIKeyRequired || definition.APIKeyRequired
+		if len(definition.ExtraParams) != 0 {
+			extraParams, err := jsonvalue.CopyMap(definition.ExtraParams)
+			if err != nil {
+				return nil, err
+			}
+			resolved.ExtraParams = extraParams
+		}
+	}
+	resolved.ID = chain[0].ID
+	resolved.BaseProfileID = ""
+	return resolved, nil
+}
+
+func validateResolvedProfile(profile *domain.ExecutionProfile) error {
+	if profile == nil {
+		return errors.New("resolved profile is required")
+	}
+	profile.BaseProfileID = ""
+	return NormalizeAndValidateDefinition(profile)
+}

internal/profile/resolving_repository_test.go

@@ -0,0 +1,418 @@
+package profile
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io/fs"
+	"reflect"
+	"strings"
+	"sync"
+	"testing"
+	"testing/fstest"
+
+	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
+)
+
+func TestResolvingRepositoryMergesProfileChain(t *testing.T) {
+	repo := &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+		"leaf": {
+			ID:              "leaf",
+			BaseProfileID:   "middle",
+			BackendID:       "leaf-backend",
+			TopP:            0.8,
+			TimeoutSeconds:  45,
+			ReasoningEffort: "high",
+		},
+		"middle": {
+			ID:             "middle",
+			BaseProfileID:  "root",
+			Endpoint:       "https://middle.example/v1",
+			Model:          "middle-model",
+			MaxTokens:      256,
+			APIKeyEnv:      "MIDDLE_API_KEY",
+			APIKeyRequired: true,
+			ExtraParams:    map[string]any{"middle": map[string]any{"value": "middle"}},
+		},
+		"root": {
+			ID:          "root",
+			BackendID:   "root-backend",
+			Endpoint:    "https://root.example/v1",
+			Model:       "root-model",
+			Temperature: 0.3,
+			ServiceTier: "priority",
+			ExtraParams: map[string]any{"root": "value"},
+		},
+	}}
+
+	got, err := NewResolvingRepository(repo).GetProfile(context.Background(), "leaf")
+	if err != nil {
+		t.Fatalf("resolve profile: %v", err)
+	}
+	want := &domain.ExecutionProfile{
+		ID:              "leaf",
+		BackendID:       "leaf-backend",
+		Endpoint:        "https://middle.example/v1",
+		Model:           "middle-model",
+		Temperature:     0.3,
+		MaxTokens:       256,
+		TopP:            0.8,
+		TimeoutSeconds:  45,
+		ServiceTier:     "priority",
+		ReasoningEffort: "high",
+		APIKeyEnv:       "MIDDLE_API_KEY",
+		APIKeyRequired:  true,
+		ExtraParams:     map[string]any{"middle": map[string]any{"value": "middle"}},
+	}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("resolved profile:\n got %#v\nwant %#v", got, want)
+	}
+}
+
+func TestResolvingRepositoryRejectsMissingSourceAndProfileID(t *testing.T) {
+	if _, err := NewResolvingRepository(nil).GetProfile(context.Background(), "profile"); !errors.Is(err, ErrInvalidProfile) {
+		t.Fatalf("nil source error = %v, want ErrInvalidProfile", err)
+	}
+
+	repo := &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{}}
+	if _, err := NewResolvingRepository(repo).GetProfile(context.Background(), " \t "); !errors.Is(err, ErrInvalidProfile) {
+		t.Fatalf("blank id error = %v, want ErrInvalidProfile", err)
+	}
+	if got := repo.callCount(" "); got != 0 {
+		t.Fatalf("blank id looked up source %d times", got)
+	}
+}
+
+func TestResolvingRepositoryCopiesExtraParams(t *testing.T) {
+	baseParams := map[string]any{"nested": map[string]any{"value": "base"}}
+	repo := &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+		"child": {ID: "child", BaseProfileID: "base"},
+		"base": {
+			ID:          "base",
+			Endpoint:    "https://base.example/v1",
+			Model:       "model",
+			ExtraParams: baseParams,
+		},
+	}}
+	resolver := NewResolvingRepository(repo)
+
+	first, err := resolver.GetProfile(context.Background(), "child")
+	if err != nil {
+		t.Fatalf("resolve inherited map: %v", err)
+	}
+	first.ExtraParams["nested"].(map[string]any)["value"] = "mutated"
+	second, err := resolver.GetProfile(context.Background(), "child")
+	if err != nil {
+		t.Fatalf("resolve inherited map again: %v", err)
+	}
+	if got := second.ExtraParams["nested"].(map[string]any)["value"]; got != "base" {
+		t.Fatalf("later result retained mutation: %v", got)
+	}
+	if got := baseParams["nested"].(map[string]any)["value"]; got != "base" {
+		t.Fatalf("source map retained mutation: %v", got)
+	}
+
+	repo.set("child", &domain.ExecutionProfile{
+		ID:            "child",
+		BaseProfileID: "base",
+		ExtraParams:   map[string]any{"child": "replacement"},
+	})
+	replaced, err := resolver.GetProfile(context.Background(), "child")
+	if err != nil {
+		t.Fatalf("resolve replacement map: %v", err)
+	}
+	if !reflect.DeepEqual(replaced.ExtraParams, map[string]any{"child": "replacement"}) {
+		t.Fatalf("extra params = %#v, want complete child replacement", replaced.ExtraParams)
+	}
+}
+
+func TestResolvingRepositoryUsesRawOverlayForEachLookup(t *testing.T) {
+	leafSource := NewFSRepository(profileTestFS(map[string]string{
+		"leaf.yaml": "id: leaf\nbase_profile: base\n",
+	}), ".")
+	fallback := NewFSRepository(profileTestFS(map[string]string{
+		"base.yaml": "id: base\nendpoint: https://fallback.example/v1\nmodel: fallback-model\n",
+	}), ".")
+	overlay := NewOverlayRepository(leafSource, fallback)
+	resolver := NewResolvingRepository(overlay)
+
+	got, err := resolver.GetProfile(context.Background(), "leaf")
+	if err != nil {
+		t.Fatalf("resolve fallback base: %v", err)
+	}
+	if got.Model != "fallback-model" {
+		t.Fatalf("fallback base model = %q", got.Model)
+	}
+
+	shadowing := NewOverlayRepository(NewFSRepository(profileTestFS(map[string]string{
+		"leaf.yaml": "id: leaf\nbase_profile: base\n",
+		"base.yaml": "id: base\nendpoint: https://primary.example/v1\nmodel: primary-model\n",
+	}), "."), fallback)
+	got, err = NewResolvingRepository(shadowing).GetProfile(context.Background(), "leaf")
+	if err != nil {
+		t.Fatalf("resolve shadowed base: %v", err)
+	}
+	if got.Model != "primary-model" || got.Endpoint != "https://primary.example/v1" {
+		t.Fatalf("shadowed base = %+v", got)
+	}
+}
+
+func TestResolvingRepositoryReportsSafetyAndSourceErrors(t *testing.T) {
+	sourceErr := errors.New("source failure")
+	tests := []struct {
+		name     string
+		repo     *resolvingTestRepository
+		id       string
+		want     []error
+		wantNot  error
+		contains []string
+	}{
+		{
+			name:    "missing selected profile preserves not found",
+			repo:    &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{}},
+			id:      "missing",
+			want:    []error{ErrProfileNotFound},
+			wantNot: ErrInvalidProfile,
+		},
+		{
+			name: "missing base is invalid but not not found",
+			repo: &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+				"leaf": {ID: "leaf", BaseProfileID: "missing"},
+			}},
+			id:       "leaf",
+			want:     []error{ErrInvalidProfile},
+			wantNot:  ErrProfileNotFound,
+			contains: []string{"missing", "leaf -> missing"},
+		},
+		{
+			name: "direct cycle",
+			repo: &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+				"a": {ID: "a", BaseProfileID: "a"},
+			}},
+			id:       "a",
+			want:     []error{ErrInvalidProfile},
+			contains: []string{"a -> a"},
+		},
+		{
+			name: "indirect cycle",
+			repo: &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+				"a": {ID: "a", BaseProfileID: "b"},
+				"b": {ID: "b", BaseProfileID: "c"},
+				"c": {ID: "c", BaseProfileID: "a"},
+			}},
+			id:       "a",
+			want:     []error{ErrInvalidProfile},
+			contains: []string{"a -> b -> c -> a"},
+		},
+		{
+			name: "nil result",
+			repo: &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+				"leaf": nil,
+			}},
+			id:   "leaf",
+			want: []error{ErrInvalidProfile},
+		},
+		{
+			name: "incomplete resolved profile",
+			repo: &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+				"leaf": {ID: "leaf", BaseProfileID: "base"},
+				"base": {ID: "base", Model: "model"},
+			}},
+			id:   "leaf",
+			want: []error{ErrInvalidProfile},
+		},
+		{
+			name: "base source error is retained",
+			repo: &resolvingTestRepository{
+				profiles: map[string]*domain.ExecutionProfile{"leaf": {ID: "leaf", BaseProfileID: "base"}},
+				errors:   map[string]error{"base": sourceErr},
+			},
+			id:   "leaf",
+			want: []error{ErrInvalidProfile, sourceErr},
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			_, err := NewResolvingRepository(tc.repo).GetProfile(context.Background(), tc.id)
+			for _, want := range tc.want {
+				if !errors.Is(err, want) {
+					t.Fatalf("error = %v, want %v", err, want)
+				}
+			}
+			if tc.wantNot != nil && errors.Is(err, tc.wantNot) {
+				t.Fatalf("error = %v, must not match %v", err, tc.wantNot)
+			}
+			for _, fragment := range tc.contains {
+				if !strings.Contains(err.Error(), fragment) {
+					t.Fatalf("error = %v, want %q", err, fragment)
+				}
+			}
+		})
+	}
+}
+
+func TestResolvingRepositoryEnforcesChainLength(t *testing.T) {
+	for _, count := range []int{maximumProfileChainLength, maximumProfileChainLength + 1} {
+		t.Run(fmt.Sprintf("%d profiles", count), func(t *testing.T) {
+			profiles := make(map[string]*domain.ExecutionProfile, count)
+			for index := 1; index <= count; index++ {
+				id := fmt.Sprintf("profile-%d", index)
+				definition := &domain.ExecutionProfile{ID: id}
+				if index == count {
+					definition.Endpoint = "https://root.example/v1"
+					definition.Model = "model"
+				} else {
+					definition.BaseProfileID = fmt.Sprintf("profile-%d", index+1)
+				}
+				profiles[id] = definition
+			}
+
+			got, err := NewResolvingRepository(&resolvingTestRepository{profiles: profiles}).GetProfile(context.Background(), "profile-1")
+			if count == maximumProfileChainLength {
+				if err != nil || got == nil {
+					t.Fatalf("profile = %+v, error = %v, want accepted chain", got, err)
+				}
+				return
+			}
+			if !errors.Is(err, ErrInvalidProfile) {
+				t.Fatalf("error = %v, want ErrInvalidProfile", err)
+			}
+		})
+	}
+}
+
+func TestResolvingRepositoryIsFreshAndCancellationAware(t *testing.T) {
+	repo := &resolvingTestRepository{profiles: map[string]*domain.ExecutionProfile{
+		"leaf": {ID: "leaf", BaseProfileID: "base"},
+		"base": {ID: "base", Endpoint: "https://base.example/v1", Model: "first", ExtraParams: map[string]any{"nested": map[string]any{"value": "first"}}},
+	}}
+	resolver := NewResolvingRepository(repo)
+
+	first, err := resolver.GetProfile(context.Background(), "leaf")
+	if err != nil || first.Model != "first" {
+		t.Fatalf("first result=(%+v, %v)", first, err)
+	}
+	repo.set("base", &domain.ExecutionProfile{ID: "base", Endpoint: "https://base.example/v1", Model: "second", ExtraParams: map[string]any{"nested": map[string]any{"value": "second"}}})
+	second, err := resolver.GetProfile(context.Background(), "leaf")
+	if err != nil || second.Model != "second" {
+		t.Fatalf("second result=(%+v, %v)", second, err)
+	}
+
+	canceled, cancel := context.WithCancel(context.Background())
+	cancel()
+	if _, err := resolver.GetProfile(canceled, "leaf"); !errors.Is(err, context.Canceled) {
+		t.Fatalf("canceled lookup error = %v", err)
+	}
+	if got := repo.callCount("leaf"); got != 2 {
+		t.Fatalf("calls after canceled lookup = %d, want 2", got)
+	}
+
+	duringTraversal, cancelDuringTraversal := context.WithCancel(context.Background())
+	repo.afterGet = func(id string) {
+		if id == "leaf" {
+			cancelDuringTraversal()
+		}
+	}
+	if _, err := resolver.GetProfile(duringTraversal, "leaf"); !errors.Is(err, context.Canceled) {
+		t.Fatalf("during traversal error = %v", err)
+	}
+	if got := repo.callCount("base"); got != 2 {
+		t.Fatalf("base calls after cancellation = %d, want 2", got)
+	}
+
+	terminalLookup, cancelTerminalLookup := context.WithCancel(context.Background())
+	repo.afterGet = func(id string) {
+		if id == "base" {
+			cancelTerminalLookup()
+		}
+	}
+	if _, err := resolver.GetProfile(terminalLookup, "leaf"); !errors.Is(err, context.Canceled) {
+		t.Fatalf("terminal lookup cancellation error = %v", err)
+	}
+	if got := repo.callCount("base"); got != 3 {
+		t.Fatalf("base calls after terminal cancellation = %d, want 3", got)
+	}
+
+	repo.afterGet = nil
+	var wg sync.WaitGroup
+	errors := make(chan error, 8)
+	for index := 0; index < cap(errors); index++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			resolved, err := resolver.GetProfile(context.Background(), "leaf")
+			if err != nil {
+				errors <- err
+				return
+			}
+			resolved.ExtraParams["nested"].(map[string]any)["value"] = "mutated"
+		}()
+	}
+	wg.Wait()
+	close(errors)
+	for err := range errors {
+		t.Errorf("concurrent resolution: %v", err)
+	}
+	latest, err := resolver.GetProfile(context.Background(), "leaf")
+	if err != nil || latest.ExtraParams["nested"].(map[string]any)["value"] != "second" {
+		t.Fatalf("latest result=(%+v, %v)", latest, err)
+	}
+}
+
+type resolvingTestRepository struct {
+	mu       sync.Mutex
+	profiles map[string]*domain.ExecutionProfile
+	errors   map[string]error
+	calls    map[string]int
+	afterGet func(string)
+}
+
+func (r *resolvingTestRepository) GetProfile(ctx context.Context, id string) (*domain.ExecutionProfile, error) {
+	if err := ctx.Err(); err != nil {
+		return nil, err
+	}
+	r.mu.Lock()
+	if r.calls == nil {
+		r.calls = make(map[string]int)
+	}
+	r.calls[id]++
+	err := r.errors[id]
+	profile := r.profiles[id]
+	afterGet := r.afterGet
+	r.mu.Unlock()
+	if afterGet != nil {
+		afterGet(id)
+	}
+	if err != nil {
+		return nil, err
+	}
+	if profile == nil {
+		if _, exists := r.profiles[id]; exists {
+			return nil, nil
+		}
+		return nil, ErrProfileNotFound
+	}
+	copy := *profile
+	return &copy, nil
+}
+
+func (r *resolvingTestRepository) set(id string, profile *domain.ExecutionProfile) {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	r.profiles[id] = profile
+}
+
+func (r *resolvingTestRepository) callCount(id string) int {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	return r.calls[id]
+}
+
+func profileTestFS(files map[string]string) fs.FS {
+	fsys := make(fstest.MapFS, len(files))
+	for name, content := range files {
+		fsys[name] = profileMapFile(content)
+	}
+	return fsys
+}

internal/promptdef/repository_test.go

@@ -892,6 +892,38 @@ output:
   format: text
   validation_mode: none
   repair_attempts: -1
+`,
+			wantErr:        true,
+			wantDiagnostic: "repair_attempts",
+		},
+		{
+			name: "repair attempts above maximum",
+			definition: `
+id: normalization-rule
+version: "1"
+messages:
+  - role: user
+    content: test
+output:
+  format: text
+  validation_mode: basic
+  repair_attempts: 4
+`,
+			wantErr:        true,
+			wantDiagnostic: "repair_attempts",
+		},
+		{
+			name: "none validation with repair attempts",
+			definition: `
+id: normalization-rule
+version: "1"
+messages:
+  - role: user
+    content: test
+output:
+  format: text
+  validation_mode: none
+  repair_attempts: 1
 `,
 			wantErr:        true,
 			wantDiagnostic: "repair_attempts",

internal/usecase/output_contract_test.go

@@ -106,6 +106,8 @@ func TestRunnerPreparationRejectsInvalidOutputContractsBeforeCompletion(t *testi
 		{name: "unsupported format", override: domain.OutputContract{Format: "binary", ValidationMode: domain.ValidationNone}},
 		{name: "empty validation mode", override: domain.OutputContract{Format: domain.FormatText}},
 		{name: "negative repair attempts", override: domain.OutputContract{Format: domain.FormatText, ValidationMode: domain.ValidationNone, RepairAttempts: -1}},
+		{name: "repair attempts above maximum", override: domain.OutputContract{Format: domain.FormatText, ValidationMode: domain.ValidationBasic, RepairAttempts: 4}},
+		{name: "none validation with repair attempts", override: domain.OutputContract{Format: domain.FormatText, ValidationMode: domain.ValidationNone, RepairAttempts: 1}},
 		{name: "json schema without path", override: domain.OutputContract{Format: domain.FormatJSON, ValidationMode: domain.ValidationJSONSchema}},
 	}
 

internal/usecase/prepared_execution_test.go

@@ -3,11 +3,12 @@ package usecase
 import (
 	"context"
 	"errors"
-	"os"
+	"fmt"
 	"reflect"
 	"testing"
 
 	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
+	"gitea.maximumdirect.net/eric/promptkit/internal/llm"
 	"gitea.maximumdirect.net/eric/promptkit/internal/validate"
 )
 
@@ -241,49 +242,76 @@ func excessivelyDeepPreparedJSONValue() any {
 	return value
 }
 
-func TestRunnerRunPreparedRechecksEnvironmentCredentialBeforeAdmission(t *testing.T) {
+func TestRunnerRunPreparedCredentialAvailabilityBeforeAdmission(t *testing.T) {
 	const environmentName = "PROMPTKIT_PREPARED_EXECUTION_TEST_KEY"
-	t.Setenv(environmentName, "available-during-preparation")
+	tests := []struct {
-
+		name           string
-	profile := defaultExecutionProfile()
+		apiKeyRequired bool
-	profile.APIKeyEnv = environmentName
+		profileEnv     bool
-	validator := &recordingValidationPreparer{plan: &recordingPreparedValidation{}}
+		overrideEnv    bool
-	admitter := &fakeRunAdmitter{}
+		wantFailure    bool
-	llmClient := &fakeLLM{resp: &domain.GenerateResponse{Content: "unexpected"}}
+	}{
-	runner := NewRunner(
+		{name: "optional environment becomes unavailable", profileEnv: true},
-		&fakePromptRepo{def: promptDef(domain.FormatText, domain.ValidationNone, 0)},
+		{
-		&fakeExecutionProfileRepo{profiles: map[string]*domain.ExecutionProfile{"exec": profile}},
+			name:           "required request environment becomes unavailable",
-		nil,
+			apiKeyRequired: true,
-		defaultArtifactReader(),
+			overrideEnv:    true,
-		defaultRenderer(),
+			wantFailure:    true,
-		llmClient,
+		},
-		validator,
-		admitter,
-	)
-	prepared, err := runner.PrepareExecution(context.Background(), domain.RunRequest{
-		PromptID:  "p",
-		ProfileID: "exec",
-		Inputs:    singleInputRef(),
-	})
-	if err != nil {
-		t.Fatalf("prepare execution: %v", err)
-	}
-	if err := os.Unsetenv(environmentName); err != nil {
-		t.Fatalf("unset credential environment: %v", err)
 	}
 
-	result, err := runner.RunPrepared(context.Background(), prepared)
+	for _, tc := range tests {
-	if result != nil {
+		t.Run(tc.name, func(t *testing.T) {
-		t.Fatalf("credential failure returned partial result: %+v", result)
+			t.Setenv(environmentName, "available-during-preparation")
-	}
+
-	if !errors.Is(err, ErrInvalidRequest) || !errors.Is(err, ErrAPIKeyEnvMissing) {
+			profile := defaultExecutionProfile()
-		t.Fatalf("credential error identities are missing: %v", err)
+			profile.APIKeyRequired = tc.apiKeyRequired
-	}
+			if tc.profileEnv {
-	if len(admitter.backendIDs) != 0 || llmClient.calls != 0 {
+				profile.APIKeyEnv = environmentName
-		t.Fatalf("credential failure reached admission or generation: admission=%v generation=%d", admitter.backendIDs, llmClient.calls)
+			}
-	}
+			validator := &recordingValidationPreparer{plan: &recordingPreparedValidation{}}
-	if _, err := runner.RunPrepared(context.Background(), prepared); !errors.Is(err, ErrInvalidRequest) {
+			admitter := &fakeRunAdmitter{}
-		t.Fatalf("credential failure did not consume execution: %v", err)
+			llmClient := &fakeLLM{resp: &domain.GenerateResponse{Content: "ok"}}
+			runner := NewRunner(
+				&fakePromptRepo{def: promptDef(domain.FormatText, domain.ValidationNone, 0)},
+				&fakeExecutionProfileRepo{profiles: map[string]*domain.ExecutionProfile{"exec": profile}},
+				nil,
+				defaultArtifactReader(),
+				defaultRenderer(),
+				llmClient,
+				validator,
+				admitter,
+			)
+			request := domain.RunRequest{PromptID: "p", ProfileID: "exec", Inputs: singleInputRef()}
+			if tc.overrideEnv {
+				request.Execution = &domain.ExecutionTargetOverride{APIKeyEnv: environmentName}
+			}
+			prepared, err := runner.PrepareExecution(context.Background(), request)
+			if err != nil {
+				t.Fatalf("prepare execution: %v", err)
+			}
+			t.Setenv(environmentName, "")
+
+			result, err := runner.RunPrepared(context.Background(), prepared)
+			if tc.wantFailure {
+				if result != nil || !errors.Is(err, ErrInvalidRequest) || !errors.Is(err, ErrAPIKeyEnvMissing) {
+					t.Fatalf("required credential result = (%+v, %v)", result, err)
+				}
+				if len(admitter.backendIDs) != 0 || llmClient.calls != 0 {
+					t.Fatalf("required credential reached admission or generation: admission=%v generation=%d", admitter.backendIDs, llmClient.calls)
+				}
+			} else {
+				if result == nil || err != nil {
+					t.Fatalf("optional credential result = (%+v, %v), want success", result, err)
+				}
+				if len(admitter.backendIDs) != 1 || llmClient.calls != 1 {
+					t.Fatalf("optional credential admission=%v generation=%d, want one each", admitter.backendIDs, llmClient.calls)
+				}
+			}
+			if _, err := runner.RunPrepared(context.Background(), prepared); !errors.Is(err, ErrInvalidRequest) {
+				t.Fatalf("execution outcome did not consume handle: %v", err)
+			}
+		})
 	}
 }
 
@@ -359,19 +387,20 @@ func TestRunnerRunPreparedUsesFrozenValidationForInitialAndRepairOutputs(t *test
 	admitter := &fakeRunAdmitter{}
 	reader := defaultArtifactReader()
 	renderer := defaultRenderer()
+	client := &sequenceLLM{responses: []*domain.GenerateResponse{{
+		Content: `{"broken":true}`,
+		Usage: domain.TokenUsage{
+			PromptTokens: 13, CompletionTokens: 17, TotalTokens: 19,
+			CachedTokens: 23, CacheWriteTokens: 29,
+		},
+	}}}
 	runner := NewRunnerWithRepairer(
 		&fakePromptRepo{def: promptDef(domain.FormatJSON, domain.ValidationJSON, 1)},
 		&fakeExecutionProfileRepo{profiles: map[string]*domain.ExecutionProfile{"exec": defaultExecutionProfile()}},
 		nil,
 		reader,
 		renderer,
-		&fakeLLM{resp: &domain.GenerateResponse{
+		client,
-			Content: `{"broken":true}`,
-			Usage: domain.TokenUsage{
-				PromptTokens: 13, CompletionTokens: 17, TotalTokens: 19,
-				CachedTokens: 23, CacheWriteTokens: 29,
-			},
-		}},
 		validator,
 		repairer,
 		admitter,
@@ -395,6 +424,10 @@ func TestRunnerRunPreparedUsesFrozenValidationForInitialAndRepairOutputs(t *test
 	if validator.directValidateCalls != 0 || repairer.calls != 1 {
 		t.Fatalf("validation/repair calls=(direct=%d repair=%d), want (0, 1)", validator.directValidateCalls, repairer.calls)
 	}
+	if len(client.requests) != 1 || len(repairer.reqs) != 1 ||
+		!reflect.DeepEqual(repairer.reqs[0].OriginalMessages, client.requests[0].Prompt.Messages) {
+		t.Fatalf("initial and repair messages = (%#v, %#v)", client.requests, repairer.reqs)
+	}
 	if result.Validation.Status != domain.ValidationPassed || result.Validation.RepairAttempts != 1 {
 		t.Fatalf("unexpected repaired validation result: %+v", result.Validation)
 	}
@@ -417,6 +450,7 @@ func TestRunnerRunPreparedReleasesAdmissionAcrossExecutionErrors(t *testing.T) {
 	generationFailure := errors.New("generation failed")
 	validationFailure := errors.New("validation failed")
 	repairFailure := errors.New("repair failed")
+	repairInvalidRequest := fmt.Errorf("repair request: %w", llm.ErrInvalidRequest)
 
 	tests := []struct {
 		name          string
@@ -424,6 +458,7 @@ func TestRunnerRunPreparedReleasesAdmissionAcrossExecutionErrors(t *testing.T) {
 		validation    *recordingPreparedValidation
 		repairer      *fakeRepairer
 		wantError     error
+		wantSource    error
 	}{
 		{
 			name:          "generation failure",
@@ -448,8 +483,51 @@ func TestRunnerRunPreparedReleasesAdmissionAcrossExecutionErrors(t *testing.T) {
 					IsValid: false,
 				}},
 			},
-			repairer:  &fakeRepairer{err: repairFailure},
+			repairer:   &fakeRepairer{err: repairFailure},
-			wantError: ErrValidation,
+			wantError:  ErrLLMGenerate,
+			wantSource: repairFailure,
+		},
+		{
+			name: "repair invalid request",
+			validation: &recordingPreparedValidation{
+				results: []domain.ValidationResult{{
+					Status:  domain.ValidationFailed,
+					Mode:    domain.ValidationJSON,
+					Errors:  []string{"invalid"},
+					IsValid: false,
+				}},
+			},
+			repairer:   &fakeRepairer{err: repairInvalidRequest},
+			wantError:  ErrInvalidRequest,
+			wantSource: repairInvalidRequest,
+		},
+		{
+			name: "repair cancellation",
+			validation: &recordingPreparedValidation{
+				results: []domain.ValidationResult{{
+					Status:  domain.ValidationFailed,
+					Mode:    domain.ValidationJSON,
+					Errors:  []string{"invalid"},
+					IsValid: false,
+				}},
+			},
+			repairer:   &fakeRepairer{err: context.Canceled},
+			wantError:  ErrLLMGenerate,
+			wantSource: context.Canceled,
+		},
+		{
+			name: "repair deadline",
+			validation: &recordingPreparedValidation{
+				results: []domain.ValidationResult{{
+					Status:  domain.ValidationFailed,
+					Mode:    domain.ValidationJSON,
+					Errors:  []string{"invalid"},
+					IsValid: false,
+				}},
+			},
+			repairer:   &fakeRepairer{err: context.DeadlineExceeded},
+			wantError:  ErrLLMGenerate,
+			wantSource: context.DeadlineExceeded,
 		},
 	}
 
@@ -488,6 +566,9 @@ func TestRunnerRunPreparedReleasesAdmissionAcrossExecutionErrors(t *testing.T) {
 			if result != nil || !errors.Is(err, test.wantError) {
 				t.Fatalf("run prepared=(%+v, %v), want %v", result, err, test.wantError)
 			}
+			if test.wantSource != nil && !errors.Is(err, test.wantSource) {
+				t.Fatalf("run prepared error = %v, want source %v", err, test.wantSource)
+			}
 			if len(admitter.backendIDs) != 1 || admitter.releaseCalls != 1 {
 				t.Fatalf(
 					"admission calls=%#v releases=%d, want one each",

internal/usecase/repairer.go

@@ -2,19 +2,29 @@ package usecase
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"strings"
+	"unicode/utf8"
 
 	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
 	"gitea.maximumdirect.net/eric/promptkit/internal/llm"
 )
 
+const (
+	maxRepairDiagnosticBytes = 64 * 1024
+	omittedRepairDiagnostics = "additional validation diagnostics were omitted"
+)
+
+// OutputRepairer generates a corrected candidate after validation fails.
 type OutputRepairer interface {
 	Repair(ctx context.Context, req RepairRequest) (*domain.GenerateResponse, error)
 }
 
+// RepairRequest contains the immutable execution state needed for one correction.
 type RepairRequest struct {
+	OriginalMessages []domain.RenderedMessage
 	PreviousOutput   string
 	ValidationErrors []string
 	SessionID        string
@@ -30,6 +40,7 @@ type defaultOutputRepairer struct {
 	llm llm.Client
 }
 
+// NewDefaultOutputRepairer constructs the standard internal output repairer.
 func NewDefaultOutputRepairer(llmClient llm.Client) OutputRepairer {
 	return &defaultOutputRepairer{llm: llmClient}
 }
@@ -39,33 +50,42 @@ func (r *defaultOutputRepairer) Repair(ctx context.Context, req RepairRequest) (
 		return nil, errors.New("llm client is required for repair")
 	}
 
-	errs := "(none provided)"
+	guidance, err := repairGuidance(req.Mode)
-	if len(req.ValidationErrors) > 0 {
+	if err != nil {
-		errs = strings.Join(req.ValidationErrors, "\n")
+		return nil, err
 	}
 
-	prompt := domain.RenderedPrompt{
+	messages := make([]domain.RenderedMessage, len(req.OriginalMessages), len(req.OriginalMessages)+2)
-		Messages: []domain.RenderedMessage{
+	copy(messages, req.OriginalMessages)
-			{
+	if strings.TrimSpace(req.PreviousOutput) != "" {
-				Role:    "system",
+		messages = append(messages, domain.RenderedMessage{
-				Content: "You repair invalid JSON output. Return only corrected JSON. Do not include explanations or markdown code fences.",
+			Role:    "assistant",
-			},
+			Content: req.PreviousOutput,
-			{
+		})
-				Role: "user",
-				Content: fmt.Sprintf(
-					"Repair attempt %d of %d for validation mode %s.\n\nValidation errors:\n%s\n\nPrevious output:\n%s\n\nReturn only corrected JSON.",
-					req.Attempt,
-					req.MaxAttempts,
-					req.Mode,
-					errs,
-					req.PreviousOutput,
-				),
-			},
-		},
 	}
 
+	previousResponse := "The previous response was empty."
+	if strings.TrimSpace(req.PreviousOutput) != "" {
+		previousResponse = "The previous response is included immediately before this instruction."
+	}
+	messages = append(messages, domain.RenderedMessage{
+		Role: "user",
+		Content: fmt.Sprintf(
+			"Repair attempt %d of %d for validation mode %s.\n"+
+				"Preserve valid values and change only what is necessary.\n"+
+				"%s\n%s\n"+
+				"Validation diagnostics (data):\n%s",
+			req.Attempt,
+			req.MaxAttempts,
+			req.Mode,
+			previousResponse,
+			guidance,
+			formatRepairDiagnostics(req.ValidationErrors),
+		),
+	})
+
 	resp, err := r.llm.Generate(ctx, newGenerationRequest(
-		prompt,
+		domain.RenderedPrompt{Messages: messages},
 		req.SessionID,
 		req.Target,
 		req.TargetPresence,
@@ -80,3 +100,90 @@ func (r *defaultOutputRepairer) Repair(ctx context.Context, req RepairRequest) (
 
 	return resp, nil
 }
+
+func repairGuidance(mode domain.ValidationMode) (string, error) {
+	switch mode {
+	case domain.ValidationBasic:
+		return "Return a nonempty response satisfying the original request.", nil
+	case domain.ValidationJSON, domain.ValidationJSONSchema:
+		return "Return only corrected JSON, with no explanation or Markdown fences.", nil
+	default:
+		return "", fmt.Errorf("unsupported validation mode for repair: %q", mode)
+	}
+}
+
+func formatRepairDiagnostics(errors []string) string {
+	diagnostics := make([]string, len(errors))
+	for index, diagnostic := range errors {
+		diagnostics[index] = strings.ToValidUTF8(diagnostic, "\uFFFD")
+	}
+
+	complete, _ := json.Marshal(diagnostics)
+	if len(complete) <= maxRepairDiagnosticBytes {
+		return string(complete)
+	}
+
+	omission, _ := json.Marshal(omittedRepairDiagnostics)
+	encoded := make([]byte, 0, maxRepairDiagnosticBytes)
+	encoded = append(encoded, '[')
+	for _, diagnostic := range diagnostics {
+		entry, _ := json.Marshal(diagnostic)
+		separator := 0
+		if len(encoded) > 1 {
+			separator = 1
+		}
+		available := maxRepairDiagnosticBytes - len(encoded) - separator - 1 - len(omission) - 1
+		if len(entry) <= available {
+			if separator != 0 {
+				encoded = append(encoded, ',')
+			}
+			encoded = append(encoded, entry...)
+			continue
+		}
+
+		if available < len(`""`) {
+			break
+		}
+		if separator != 0 {
+			encoded = append(encoded, ',')
+		}
+		encoded = append(encoded, truncateDiagnosticJSONValue(diagnostic, available)...)
+		break
+	}
+	if len(encoded) > 1 {
+		encoded = append(encoded, ',')
+	}
+	encoded = append(encoded, omission...)
+	encoded = append(encoded, ']')
+	return string(encoded)
+}
+
+func truncateDiagnosticJSONValue(value string, maxBytes int) []byte {
+	if maxBytes < len(`""`) {
+		return nil
+	}
+
+	boundaries := []int{0}
+	for end := 0; end < len(value); {
+		_, size := utf8.DecodeRuneInString(value[end:])
+		end += size
+		if end+len(`""`) > maxBytes {
+			break
+		}
+		boundaries = append(boundaries, end)
+	}
+
+	low, high := 0, len(boundaries)-1
+	best := []byte(`""`)
+	for low <= high {
+		mid := low + (high-low)/2
+		candidate, _ := json.Marshal(value[:boundaries[mid]])
+		if len(candidate) <= maxBytes {
+			best = candidate
+			low = mid + 1
+			continue
+		}
+		high = mid - 1
+	}
+	return best
+}

internal/usecase/repairer_test.go

@@ -0,0 +1,349 @@
+package usecase
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"reflect"
+	"strings"
+	"testing"
+	"unicode/utf8"
+
+	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
+)
+
+type recordingRepairClient struct {
+	requests []domain.GenerateRequest
+	response *domain.GenerateResponse
+	err      error
+}
+
+func (c *recordingRepairClient) Generate(_ context.Context, req domain.GenerateRequest) (*domain.GenerateResponse, error) {
+	c.requests = append(c.requests, req)
+	return c.response, c.err
+}
+
+func TestDefaultOutputRepairerBuildsFullContextRequest(t *testing.T) {
+	client := &recordingRepairClient{response: &domain.GenerateResponse{Content: "corrected"}}
+	repairer := NewDefaultOutputRepairer(client)
+	original := []domain.RenderedMessage{
+		{Role: "system", Content: "Follow the task.", CacheControl: &domain.CacheControl{Type: domain.CacheControlEphemeral, TTL: "1h"}},
+		{Role: "user", Content: "Summarize the report."},
+	}
+	before := append([]domain.RenderedMessage(nil), original...)
+	previous := strings.Repeat("candidate ", 12_000)
+	target := domain.ExecutionTarget{BackendID: "backend", Endpoint: "https://provider.example/v1", Model: "model"}
+	presence := domain.ExecutionTargetPresence{Temperature: true, TopP: true}
+	structured := &domain.StructuredOutputSpec{}
+
+	response, err := repairer.Repair(context.Background(), RepairRequest{
+		OriginalMessages: original,
+		PreviousOutput:   previous,
+		ValidationErrors: []string{"invalid JSON"},
+		SessionID:        "session",
+		Target:           target,
+		TargetPresence:   presence,
+		StructuredOutput: structured,
+		Attempt:          1,
+		MaxAttempts:      3,
+		Mode:             domain.ValidationJSONSchema,
+	})
+	if err != nil {
+		t.Fatalf("repair: %v", err)
+	}
+	if response == nil || response.Content != "corrected" {
+		t.Fatalf("response = %+v", response)
+	}
+	if !reflect.DeepEqual(original, before) {
+		t.Fatalf("original messages changed: got %#v, want %#v", original, before)
+	}
+	if len(client.requests) != 1 {
+		t.Fatalf("generation requests = %d, want 1", len(client.requests))
+	}
+
+	request := client.requests[0]
+	if request.Prompt.SessionID != "session" || !reflect.DeepEqual(request.Target, target) || request.TargetPresence != presence || request.StructuredOutput != structured {
+		t.Fatalf("generation request fields = %+v", request)
+	}
+	if len(request.Prompt.Messages) != len(original)+2 {
+		t.Fatalf("message count = %d, want %d", len(request.Prompt.Messages), len(original)+2)
+	}
+	if !reflect.DeepEqual(request.Prompt.Messages[:len(original)], original) {
+		t.Fatalf("original messages = %#v, want %#v", request.Prompt.Messages[:len(original)], original)
+	}
+	assistant := request.Prompt.Messages[len(original)]
+	if assistant.Role != "assistant" || assistant.Content != previous {
+		t.Fatalf("assistant candidate = %+v", assistant)
+	}
+	correction := request.Prompt.Messages[len(original)+1]
+	if correction.Role != "user" || !strings.Contains(correction.Content, "Repair attempt 1 of 3") ||
+		!strings.Contains(correction.Content, "Preserve valid values") ||
+		!strings.Contains(correction.Content, "Return only corrected JSON") {
+		t.Fatalf("correction message = %q", correction.Content)
+	}
+	if diagnostics := repairDiagnosticsFromMessage(t, correction.Content); !reflect.DeepEqual(diagnostics, []string{"invalid JSON"}) {
+		t.Fatalf("diagnostics = %#v", diagnostics)
+	}
+}
+
+func TestDefaultOutputRepairerDoesNotAccumulateCandidates(t *testing.T) {
+	client := &recordingRepairClient{response: &domain.GenerateResponse{Content: "corrected"}}
+	repairer := NewDefaultOutputRepairer(client)
+	backing := make([]domain.RenderedMessage, 1, 4)
+	backing[0] = domain.RenderedMessage{Role: "user", Content: "Original task"}
+	before := append([]domain.RenderedMessage(nil), backing...)
+
+	for _, candidate := range []string{"first invalid", "second invalid"} {
+		_, err := repairer.Repair(context.Background(), RepairRequest{
+			OriginalMessages: backing,
+			PreviousOutput:   candidate,
+			Attempt:          1,
+			MaxAttempts:      3,
+			Mode:             domain.ValidationJSON,
+		})
+		if err != nil {
+			t.Fatalf("repair %q: %v", candidate, err)
+		}
+	}
+	if !reflect.DeepEqual(backing, before) {
+		t.Fatalf("caller messages changed: got %#v, want %#v", backing, before)
+	}
+	if len(client.requests) != 2 {
+		t.Fatalf("generation requests = %d, want 2", len(client.requests))
+	}
+	for index, request := range client.requests {
+		messages := request.Prompt.Messages
+		if len(messages) != 3 || messages[0] != backing[0] || messages[1].Role != "assistant" || messages[1].Content != []string{"first invalid", "second invalid"}[index] {
+			t.Fatalf("request %d messages = %#v", index, messages)
+		}
+	}
+}
+
+func TestDefaultOutputRepairerOmitsEmptyCandidateMessage(t *testing.T) {
+	for _, tc := range []struct {
+		name      string
+		candidate string
+	}{
+		{name: "empty", candidate: ""},
+		{name: "whitespace", candidate: " \n\t "},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			client := &recordingRepairClient{response: &domain.GenerateResponse{Content: "corrected"}}
+			repairer := NewDefaultOutputRepairer(client)
+			_, err := repairer.Repair(context.Background(), RepairRequest{
+				OriginalMessages: []domain.RenderedMessage{{Role: "user", Content: "Original task"}},
+				PreviousOutput:   tc.candidate,
+				Attempt:          1,
+				MaxAttempts:      1,
+				Mode:             domain.ValidationBasic,
+			})
+			if err != nil {
+				t.Fatalf("repair: %v", err)
+			}
+			messages := client.requests[0].Prompt.Messages
+			if len(messages) != 2 || messages[1].Role != "user" || !strings.Contains(messages[1].Content, "previous response was empty") {
+				t.Fatalf("messages = %#v", messages)
+			}
+			if strings.Contains(messages[1].Content, tc.candidate) && tc.candidate != "" {
+				t.Fatalf("correction message repeated whitespace candidate: %q", messages[1].Content)
+			}
+		})
+	}
+}
+
+func TestDefaultOutputRepairerUsesModeSpecificGuidance(t *testing.T) {
+	tests := []struct {
+		mode domain.ValidationMode
+		want string
+	}{
+		{mode: domain.ValidationBasic, want: "Return a nonempty response"},
+		{mode: domain.ValidationJSON, want: "Return only corrected JSON"},
+		{mode: domain.ValidationJSONSchema, want: "Return only corrected JSON"},
+	}
+
+	for _, tc := range tests {
+		t.Run(string(tc.mode), func(t *testing.T) {
+			client := &recordingRepairClient{response: &domain.GenerateResponse{Content: "corrected"}}
+			_, err := NewDefaultOutputRepairer(client).Repair(context.Background(), RepairRequest{Mode: tc.mode, Attempt: 1, MaxAttempts: 1})
+			if err != nil {
+				t.Fatalf("repair: %v", err)
+			}
+			if !strings.Contains(client.requests[0].Prompt.Messages[0].Content, tc.want) {
+				t.Fatalf("correction message = %q", client.requests[0].Prompt.Messages[0].Content)
+			}
+		})
+	}
+
+	client := &recordingRepairClient{response: &domain.GenerateResponse{Content: "unexpected"}}
+	_, err := NewDefaultOutputRepairer(client).Repair(context.Background(), RepairRequest{Mode: domain.ValidationNone})
+	if err == nil || !strings.Contains(err.Error(), "unsupported validation mode") {
+		t.Fatalf("unsupported mode error = %v", err)
+	}
+	if len(client.requests) != 0 {
+		t.Fatalf("generation requests = %d, want 0", len(client.requests))
+	}
+}
+
+func TestFormatRepairDiagnosticsBoundsAndPreservesData(t *testing.T) {
+	tests := []struct {
+		name         string
+		errors       []string
+		wantOmission bool
+		check        func(*testing.T, []string)
+	}{
+		{
+			name:   "below limit",
+			errors: []string{"first", "second"},
+			check: func(t *testing.T, got []string) {
+				t.Helper()
+				if !reflect.DeepEqual(got, []string{"first", "second"}) {
+					t.Fatalf("diagnostics = %#v", got)
+				}
+			},
+		},
+		{
+			name:   "at limit",
+			errors: []string{strings.Repeat("x", maxRepairDiagnosticBytes-4)},
+			check: func(t *testing.T, got []string) {
+				t.Helper()
+				if len(got) != 1 || len(got[0]) != maxRepairDiagnosticBytes-4 {
+					t.Fatalf("diagnostics lengths = %#v", got)
+				}
+			},
+		},
+		{
+			name:         "multibyte truncation preserves prior entries",
+			errors:       []string{"first", strings.Repeat("界", maxRepairDiagnosticBytes)},
+			wantOmission: true,
+			check: func(t *testing.T, got []string) {
+				t.Helper()
+				if len(got) != 3 || got[0] != "first" || !strings.HasPrefix(strings.Repeat("界", maxRepairDiagnosticBytes), got[1]) {
+					t.Fatalf("diagnostics = %#v", got)
+				}
+			},
+		},
+		{
+			name:         "many diagnostics",
+			errors:       manyRepairDiagnostics(),
+			wantOmission: true,
+			check: func(t *testing.T, got []string) {
+				t.Helper()
+				if len(got) < 2 || got[0] != manyRepairDiagnostics()[0] {
+					t.Fatalf("diagnostics = %#v", got)
+				}
+			},
+		},
+		{
+			name: "no room for partial diagnostic",
+			errors: func() []string {
+				omission, _ := json.Marshal(omittedRepairDiagnostics)
+				return []string{
+					strings.Repeat("x", maxRepairDiagnosticBytes-len(omission)-5),
+					strings.Repeat("y", 128),
+				}
+			}(),
+			wantOmission: true,
+			check: func(t *testing.T, got []string) {
+				t.Helper()
+				if len(got) != 2 || got[1] != omittedRepairDiagnostics {
+					t.Fatalf("diagnostics = %#v", got)
+				}
+			},
+		},
+		{
+			name:   "invalid UTF-8",
+			errors: []string{"broken\xffinput"},
+			check: func(t *testing.T, got []string) {
+				t.Helper()
+				if !reflect.DeepEqual(got, []string{"broken\uFFFDinput"}) {
+					t.Fatalf("diagnostics = %#v", got)
+				}
+			},
+		},
+		{
+			name:         "one huge diagnostic",
+			errors:       []string{strings.Repeat("x", maxRepairDiagnosticBytes*2)},
+			wantOmission: true,
+			check: func(t *testing.T, got []string) {
+				t.Helper()
+				if len(got) != 2 || !strings.HasPrefix(strings.Repeat("x", maxRepairDiagnosticBytes*2), got[0]) {
+					t.Fatalf("diagnostics = %#v", got)
+				}
+			},
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			before := append([]string(nil), tc.errors...)
+			encoded := formatRepairDiagnostics(tc.errors)
+			if len(encoded) > maxRepairDiagnosticBytes || !utf8.ValidString(encoded) {
+				t.Fatalf("encoded diagnostic length/UTF-8 = (%d, %v)", len(encoded), utf8.ValidString(encoded))
+			}
+			var got []string
+			if err := json.Unmarshal([]byte(encoded), &got); err != nil {
+				t.Fatalf("decode diagnostics: %v; encoded=%q", err, encoded)
+			}
+			if !reflect.DeepEqual(tc.errors, before) {
+				t.Fatalf("input diagnostics changed: got %#v, want %#v", tc.errors, before)
+			}
+			if hasOmission := len(got) > 0 && got[len(got)-1] == omittedRepairDiagnostics; hasOmission != tc.wantOmission {
+				t.Fatalf("omission = %v, want %v; diagnostics=%#v", hasOmission, tc.wantOmission, got)
+			}
+			tc.check(t, got)
+		})
+	}
+}
+
+func manyRepairDiagnostics() []string {
+	diagnostics := make([]string, 1_000)
+	for index := range diagnostics {
+		diagnostics[index] = fmt.Sprintf("diagnostic %04d %s", index, strings.Repeat("x", 128))
+	}
+	return diagnostics
+}
+
+func TestDefaultOutputRepairerPropagatesGenerationFailures(t *testing.T) {
+	expected := errors.New("generation failed")
+	for _, tc := range []struct {
+		name   string
+		client *recordingRepairClient
+		want   error
+	}{
+		{name: "nil client", want: nil},
+		{name: "generation error", client: &recordingRepairClient{err: expected}, want: expected},
+		{name: "nil response", client: &recordingRepairClient{}, want: nil},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			var repairer OutputRepairer
+			if tc.client == nil {
+				repairer = NewDefaultOutputRepairer(nil)
+			} else {
+				repairer = NewDefaultOutputRepairer(tc.client)
+			}
+			response, err := repairer.Repair(context.Background(), RepairRequest{Mode: domain.ValidationJSON})
+			if response != nil || err == nil {
+				t.Fatalf("response/error = (%+v, %v)", response, err)
+			}
+			if tc.want != nil && !errors.Is(err, tc.want) {
+				t.Fatalf("error = %v, want %v", err, tc.want)
+			}
+		})
+	}
+}
+
+func repairDiagnosticsFromMessage(t *testing.T, message string) []string {
+	t.Helper()
+	const marker = "Validation diagnostics (data):\n"
+	index := strings.Index(message, marker)
+	if index < 0 {
+		t.Fatalf("missing diagnostics marker in %q", message)
+	}
+	encoded := message[index+len(marker):]
+	var diagnostics []string
+	if err := json.Unmarshal([]byte(encoded), &diagnostics); err != nil {
+		t.Fatalf("decode diagnostics: %v", err)
+	}
+	return diagnostics
+}

internal/usecase/runner.go

@@ -184,10 +184,10 @@ func (r *Runner) executePreparedRun(
 		prepared.StructuredOutput,
 	))
 	if err != nil {
-		if errors.Is(err, llm.ErrInvalidRequest) {
+		return nil, wrapGenerationError(err)
-			return nil, fmt.Errorf("%w: %w", ErrInvalidRequest, err)
+	}
-		}
+	if genResp == nil {
-		return nil, fmt.Errorf("%w: %w", ErrLLMGenerate, err)
+		return nil, fmt.Errorf("%w: model returned nil response", ErrLLMGenerate)
 	}
 	usage := genResp.Usage
 
@@ -203,6 +203,7 @@ func (r *Runner) executePreparedRun(
 			attemptsUsed++
 
 			repairResp, repairErr := r.repairer.Repair(ctx, RepairRequest{
+				OriginalMessages: prepared.Messages,
 				PreviousOutput:   genResp.Content,
 				ValidationErrors: validationResult.Errors,
 				SessionID:        prepared.SessionID,
@@ -214,10 +215,10 @@ func (r *Runner) executePreparedRun(
 				Mode:             prepared.OutputContract.ValidationMode,
 			})
 			if repairErr != nil {
-				return nil, fmt.Errorf("%w: %w", ErrValidation, repairErr)
+				return nil, wrapGenerationError(repairErr)
 			}
 			if repairResp == nil {
-				return nil, fmt.Errorf("%w: repairer returned nil response", ErrValidation)
+				return nil, fmt.Errorf("%w: repairer returned nil response", ErrLLMGenerate)
 			}
 
 			genResp = repairResp
@@ -257,6 +258,13 @@ func (r *Runner) executePreparedRun(
 	}, nil
 }
 
+func wrapGenerationError(err error) error {
+	if errors.Is(err, llm.ErrInvalidRequest) {
+		return fmt.Errorf("%w: %w", ErrInvalidRequest, err)
+	}
+	return fmt.Errorf("%w: %w", ErrLLMGenerate, err)
+}
+
 func addTokenUsage(total, next domain.TokenUsage) domain.TokenUsage {
 	return domain.TokenUsage{
 		PromptTokens:     total.PromptTokens + next.PromptTokens,
@@ -524,7 +532,12 @@ func (r *Runner) shouldAttemptRepair(contract domain.OutputContract, validationR
 	if validationResult.Status != domain.ValidationFailed {
 		return false
 	}
-	return contract.ValidationMode == domain.ValidationJSON || contract.ValidationMode == domain.ValidationJSONSchema
+	switch contract.ValidationMode {
+	case domain.ValidationBasic, domain.ValidationJSON, domain.ValidationJSONSchema:
+		return true
+	default:
+		return false
+	}
 }
 
 func mergeExecutionTarget(base domain.ExecutionTarget, override domain.ExecutionTarget) domain.ExecutionTarget {
@@ -624,12 +637,12 @@ func validateAPIKey(apiKeyEnv string, apiKey string, apiKeyRequired bool) error
 	if strings.TrimSpace(apiKey) != "" {
 		return nil
 	}
+	if !apiKeyRequired {
+		return nil
+	}
 	envName := strings.TrimSpace(apiKeyEnv)
 	if envName == "" {
-		if apiKeyRequired {
+		return ErrAPIKeyRequired
-			return ErrAPIKeyRequired
-		}
-		return nil
 	}
 	if strings.TrimSpace(os.Getenv(envName)) == "" {
 		return fmt.Errorf("%w: api key environment variable %q is not set", ErrAPIKeyEnvMissing, envName)

internal/usecase/runner_test.go

@@ -295,8 +295,10 @@ func (c *controlledRepairLLM) Generate(
 	ctx context.Context,
 	req domain.GenerateRequest,
 ) (*domain.GenerateResponse, error) {
-	isRepair := len(req.Prompt.Messages) > 0 &&
+	messages := req.Prompt.Messages
-		strings.HasPrefix(req.Prompt.Messages[0].Content, "You repair invalid JSON")
+	isRepair := len(messages) >= 2 &&
+		messages[len(messages)-2].Role == "assistant" &&
+		messages[len(messages)-1].Role == "user"
 	c.mu.Lock()
 	c.calls++
 	c.active++
@@ -1787,22 +1789,26 @@ func TestRunnerRunAPIKeyEnvResolvesFromEnvironment(t *testing.T) {
 	}
 }
 
-func TestRunnerRunAPIKeyEnvMissingEnvironmentValueFailsClearly(t *testing.T) {
+func TestRunnerRunOptionalAPIKeyEnvMissingEnvironmentValueReachesLLM(t *testing.T) {
+	const environmentName = "PROMPTKIT_MISSING_KEY"
+	t.Setenv(environmentName, "")
+
 	promptRepo := &fakePromptRepo{def: promptDef(domain.FormatText, domain.ValidationNone, 0)}
 	execRepo := &fakeExecutionProfileRepo{profiles: map[string]*domain.ExecutionProfile{
-		"exec": {ID: "exec", Endpoint: "http://profile/v1", Model: "profile-model", APIKeyEnv: "PROMPTKIT_MISSING_KEY"},
+		"exec": {ID: "exec", Endpoint: "http://profile/v1", Model: "profile-model", APIKeyEnv: environmentName},
 	}}
-	runner := NewRunner(promptRepo, execRepo, nil, defaultArtifactReader(), defaultRenderer(), &fakeLLM{resp: &domain.GenerateResponse{Content: "ok"}}, nil, nil)
+	llmClient := &fakeLLM{resp: &domain.GenerateResponse{Content: "ok"}}
+	runner := NewRunner(promptRepo, execRepo, nil, defaultArtifactReader(), defaultRenderer(), llmClient, nil, nil)
 
-	_, err := runner.Run(context.Background(), domain.RunRequest{PromptID: "p", ProfileID: "exec", Inputs: singleInputRef()})
+	result, err := runner.Run(context.Background(), domain.RunRequest{PromptID: "p", ProfileID: "exec", Inputs: singleInputRef()})
-	if !errors.Is(err, ErrInvalidRequest) {
+	if err != nil || result == nil {
-		t.Fatalf("expected ErrInvalidRequest, got %v", err)
+		t.Fatalf("optional credential run = (%+v, %v), want success", result, err)
 	}
-	if !errors.Is(err, ErrAPIKeyEnvMissing) {
+	if llmClient.calls != 1 {
-		t.Fatalf("expected ErrAPIKeyEnvMissing, got %v", err)
+		t.Fatalf("LLM calls = %d, want 1", llmClient.calls)
 	}
-	if !strings.Contains(err.Error(), "PROMPTKIT_MISSING_KEY") {
+	if llmClient.lastReq.Target.APIKeyEnv != environmentName {
-		t.Fatalf("expected missing env name in error, got %v", err)
+		t.Fatalf("LLM api_key_env = %q, want %q", llmClient.lastReq.Target.APIKeyEnv, environmentName)
 	}
 }
 
@@ -2139,6 +2145,8 @@ func TestRunnerRepairStateMachine(t *testing.T) {
 		TopP:           true,
 		TimeoutSeconds: true,
 	}
+	emptyThenValid := responses(2)
+	emptyThenValid[0].Content = " \t "
 
 	tests := []struct {
 		name              string
@@ -2161,12 +2169,13 @@ func TestRunnerRepairStateMachine(t *testing.T) {
 			wantStatus:        domain.ValidationPassed,
 		},
 		{
-			name:              "basic failure is ineligible despite budget",
+			name:              "empty basic output repairs successfully",
 			mode:              domain.ValidationBasic,
 			budget:            3,
-			validationResults: []domain.ValidationResult{failed(domain.ValidationBasic, "empty output")},
+			validationResults: []domain.ValidationResult{failed(domain.ValidationBasic, "empty output"), passed(domain.ValidationBasic)},
-			responses:         responses(1),
+			responses:         emptyThenValid,
-			wantStatus:        domain.ValidationFailed,
+			wantRepairs:       1,
+			wantStatus:        domain.ValidationPassed,
 		},
 		{
 			name:   "inherited numeric values remain absent",
@@ -2198,7 +2207,7 @@ func TestRunnerRepairStateMachine(t *testing.T) {
 		{
 			name:   "successful repair stops below larger budget",
 			mode:   domain.ValidationJSON,
-			budget: 4,
+			budget: 3,
 			validationResults: []domain.ValidationResult{
 				failed(domain.ValidationJSON, "candidate zero"),
 				failed(domain.ValidationJSON, "candidate one"),
@@ -2301,6 +2310,9 @@ func TestRunnerRepairStateMachine(t *testing.T) {
 					!reflect.DeepEqual(req.ValidationErrors, tc.validationResults[index].Errors) {
 					t.Fatalf("repair request %d prior state = %+v", index, req)
 				}
+				if !reflect.DeepEqual(req.OriginalMessages, initialRequest.Prompt.Messages) {
+					t.Fatalf("repair request %d original messages drifted: %#v", index, req.OriginalMessages)
+				}
 				if req.TargetPresence != tc.wantPresence || !reflect.DeepEqual(req.Target, initialRequest.Target) ||
 					req.SessionID != initialRequest.Prompt.SessionID ||
 					!reflect.DeepEqual(req.StructuredOutput, initialRequest.StructuredOutput) {
@@ -2314,8 +2326,19 @@ func TestRunnerRepairStateMachine(t *testing.T) {
 					!reflect.DeepEqual(generated.StructuredOutput, initialRequest.StructuredOutput) {
 					t.Fatalf("repair generation request %d common fields drifted: %+v", index, generated)
 				}
-				if reflect.DeepEqual(generated.Prompt.Messages, initialRequest.Prompt.Messages) {
+				expectedMessages := len(initialRequest.Prompt.Messages) + 1
-					t.Fatalf("repair generation request %d reused the initial prompt", index)
+				if strings.TrimSpace(tc.responses[index].Content) != "" {
+					expectedMessages++
+				}
+				if len(generated.Prompt.Messages) != expectedMessages ||
+					generated.Prompt.Messages[len(generated.Prompt.Messages)-1].Role != "user" {
+					t.Fatalf("repair generation request %d messages = %#v", index, generated.Prompt.Messages)
+				}
+				if strings.TrimSpace(tc.responses[index].Content) != "" {
+					assistant := generated.Prompt.Messages[len(generated.Prompt.Messages)-2]
+					if assistant.Role != "assistant" || assistant.Content != tc.responses[index].Content {
+						t.Fatalf("repair generation request %d candidate = %+v", index, assistant)
+					}
 				}
 			}
 

internal/validate/standard_validator.go

@@ -174,9 +174,8 @@ func validateArtifact(ctx context.Context, artifact *domain.Artifact, contract d
 	}
 
 	res := domain.ValidationResult{
-		Mode:           contract.ValidationMode,
+		Mode:       contract.ValidationMode,
-		SchemaPath:     contract.SchemaPath,
+		SchemaPath: contract.SchemaPath,
-		RepairAttempts: contract.RepairAttempts,
 	}
 
 	if artifact == nil {

internal/validate/standard_validator_test.go

@@ -64,6 +64,43 @@ func TestStandardValidatorBasicFailureEmpty(t *testing.T) {
 	}
 }
 
+func TestStandardValidatorReportsZeroRepairAttempts(t *testing.T) {
+	v := NewStandardValidator("")
+
+	for _, tc := range []struct {
+		name     string
+		body     string
+		contract domain.OutputContract
+	}{
+		{
+			name: "passed basic validation",
+			body: "answer",
+			contract: domain.OutputContract{
+				ValidationMode: domain.ValidationBasic,
+				RepairAttempts: 3,
+			},
+		},
+		{
+			name: "failed JSON validation",
+			body: `{"answer":`,
+			contract: domain.OutputContract{
+				ValidationMode: domain.ValidationJSON,
+				RepairAttempts: 3,
+			},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(tc.body)}, tc.contract)
+			if err != nil {
+				t.Fatalf("validate: %v", err)
+			}
+			if res.RepairAttempts != 0 {
+				t.Fatalf("repair attempts = %d, want 0", res.RepairAttempts)
+			}
+		})
+	}
+}
+
 func TestStandardValidatorJSONSuccess(t *testing.T) {
 	v := NewStandardValidator("")
 

output_contract_contract_test.go

@@ -22,27 +22,52 @@ func TestPreparationRejectsInvalidOutputContractWithPublicError(t *testing.T) {
 		t.Fatalf("construct engine: %v", err)
 	}
 
-	req := promptkit.RunRequest{
+	for _, tc := range []struct {
-		PromptID: "prompt",
+		name     string
-		Validation: &promptkit.OutputContract{
+		contract promptkit.OutputContract
-			Format:         promptkit.OutputFormat("binary"),
+	}{
-			ValidationMode: promptkit.ValidationNone,
+		{
+			name: "unsupported format",
+			contract: promptkit.OutputContract{
+				Format:         promptkit.OutputFormat("binary"),
+				ValidationMode: promptkit.ValidationNone,
+			},
 		},
-	}
+		{
+			name: "repair attempts above maximum",
+			contract: promptkit.OutputContract{
+				Format:         promptkit.FormatText,
+				ValidationMode: promptkit.ValidationBasic,
+				RepairAttempts: 4,
+			},
+		},
+		{
+			name: "none validation with repair attempts",
+			contract: promptkit.OutputContract{
+				Format:         promptkit.FormatText,
+				ValidationMode: promptkit.ValidationNone,
+				RepairAttempts: 1,
+			},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			req := promptkit.RunRequest{PromptID: "prompt", Validation: &tc.contract}
 
-	prepared, err := engine.Prepare(context.Background(), req)
+			prepared, err := engine.Prepare(context.Background(), req)
-	if prepared != nil {
+			if prepared != nil {
-		t.Fatalf("expected no partial prepared run, got %+v", prepared)
+				t.Fatalf("expected no partial prepared run, got %+v", prepared)
-	}
+			}
-	if !errors.Is(err, promptkit.ErrInvalidRequest) {
+			if !errors.Is(err, promptkit.ErrInvalidRequest) {
-		t.Fatalf("prepare error = %v, want ErrInvalidRequest", err)
+				t.Fatalf("prepare error = %v, want ErrInvalidRequest", err)
-	}
+			}
 
-	preparedExecution, err := engine.PrepareExecution(context.Background(), req)
+			preparedExecution, err := engine.PrepareExecution(context.Background(), req)
-	if preparedExecution != nil {
+			if preparedExecution != nil {
-		t.Fatalf("expected no partial prepared execution, got %+v", preparedExecution)
+				t.Fatalf("expected no partial prepared execution, got %+v", preparedExecution)
-	}
+			}
-	if !errors.Is(err, promptkit.ErrInvalidRequest) {
+			if !errors.Is(err, promptkit.ErrInvalidRequest) {
-		t.Fatalf("prepare execution error = %v, want ErrInvalidRequest", err)
+				t.Fatalf("prepare execution error = %v, want ErrInvalidRequest", err)
+			}
+		})
 	}
 }

prepared_execution_contract_test.go

@@ -5,7 +5,6 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"os"
 	"reflect"
 	"strings"
 	"sync"
@@ -257,6 +256,50 @@ func TestPreparedExecutionLifecycleAndEngineBinding(t *testing.T) {
 	}
 }
 
+func TestPreparedExecutionRepairsEmptyBasicOutput(t *testing.T) {
+	client := &preparedRecordingClient{responses: []*promptkit.GenerateResponse{
+		{
+			Content: "",
+			Usage:   promptkit.TokenUsage{PromptTokens: 3, CompletionTokens: 5, TotalTokens: 8},
+		},
+		{
+			Content: "Corrected summary.",
+			Usage:   promptkit.TokenUsage{PromptTokens: 7, CompletionTokens: 11, TotalTokens: 18},
+		},
+	}}
+	engine := newPreparedContractEngine(t, client, "Summarize the source.")
+	prepared, err := engine.PrepareExecution(context.Background(), promptkit.RunRequest{
+		PromptID: "prepared",
+		Validation: &promptkit.OutputContract{
+			Format:         promptkit.FormatMarkdown,
+			ValidationMode: promptkit.ValidationBasic,
+			RepairAttempts: 1,
+		},
+	})
+	if err != nil {
+		t.Fatalf("prepare execution: %v", err)
+	}
+	details := prepared.Details()
+
+	result, err := engine.RunPrepared(context.Background(), prepared)
+	if err != nil {
+		t.Fatalf("run prepared: %v", err)
+	}
+	if result.RawOutput != "Corrected summary." || result.Validation.Status != promptkit.ValidationPassed ||
+		result.Validation.RepairAttempts != 1 || result.Usage != (promptkit.TokenUsage{PromptTokens: 10, CompletionTokens: 16, TotalTokens: 26}) {
+		t.Fatalf("repaired result = %+v", result)
+	}
+	requests := client.snapshot()
+	if len(requests) != 2 || len(requests[1].Prompt.Messages) != len(details.Messages)+1 ||
+		!reflect.DeepEqual(requests[1].Prompt.Messages[:len(details.Messages)], details.Messages) ||
+		requests[1].Prompt.Messages[len(requests[1].Prompt.Messages)-1].Role != "user" {
+		t.Fatalf("prepared repair requests = %#v", requests)
+	}
+	if _, err := engine.RunPrepared(context.Background(), prepared); !errors.Is(err, promptkit.ErrInvalidRequest) {
+		t.Fatalf("second RunPrepared error = %v, want ErrInvalidRequest", err)
+	}
+}
+
 func TestPreparedExecutionConcurrentClaimAllowsOneGeneration(t *testing.T) {
 	release := make(chan struct{})
 	client := &preparedRecordingClient{
@@ -524,19 +567,25 @@ func TestPreparedExecutionCredentialCapacityAndTimingBoundaries(t *testing.T) {
 		engine, err := promptkit.NewEngine(
 			promptkit.Config{},
 			promptkit.WithPromptFS(contractPromptFS("prepared", "profile", "content"), "."),
-			promptkit.WithProfileFS(preparedCredentialProfileSource(environmentName), "."),
+			promptkit.WithProfiles(promptkit.Profile{
+				ID:             "profile",
+				Endpoint:       "http://example.test/v1",
+				Model:          "model",
+				APIKeyRequired: true,
+			}),
 			promptkit.WithLLMClient(client),
 		)
 		if err != nil {
 			t.Fatalf("construct credential engine: %v", err)
 		}
-		prepared, err := engine.PrepareExecution(context.Background(), promptkit.RunRequest{PromptID: "prepared"})
+		prepared, err := engine.PrepareExecution(context.Background(), promptkit.RunRequest{
+			PromptID:  "prepared",
+			Execution: &promptkit.ExecutionTargetOverride{APIKeyEnv: environmentName},
+		})
 		if err != nil {
 			t.Fatalf("prepare credential execution: %v", err)
 		}
-		if err := os.Unsetenv(environmentName); err != nil {
+		t.Setenv(environmentName, "")
-			t.Fatalf("unset credential environment: %v", err)
-		}
 
 		result, err := engine.RunPrepared(context.Background(), prepared)
 		if result != nil ||
@@ -666,12 +715,13 @@ func (r *mutablePreparedArtifactReader) callCount() int {
 }
 
 type preparedRecordingClient struct {
-	mu       sync.Mutex
+	mu        sync.Mutex
-	response *promptkit.GenerateResponse
+	response  *promptkit.GenerateResponse
-	err      error
+	responses []*promptkit.GenerateResponse
-	requests []promptkit.GenerateRequest
+	err       error
-	started  chan struct{}
+	requests  []promptkit.GenerateRequest
-	release  <-chan struct{}
+	started   chan struct{}
+	release   <-chan struct{}
 }
 
 func (c *preparedRecordingClient) Generate(
@@ -695,6 +745,12 @@ func (c *preparedRecordingClient) Generate(
 	if c.err != nil {
 		return nil, c.err
 	}
+	if len(c.responses) > 0 {
+		if index := len(c.requests) - 1; index < len(c.responses) {
+			return c.responses[index], nil
+		}
+		return nil, fmt.Errorf("no response configured for generation %d", len(c.requests))
+	}
 	return c.response, nil
 }
 
@@ -755,16 +811,6 @@ model: ` + model + `
 	}
 }
 
-func preparedCredentialProfileSource(environmentName string) fstest.MapFS {
-	return fstest.MapFS{
-		"profile.yaml": &fstest.MapFile{Data: []byte(`id: profile
-endpoint: http://example.test/v1
-model: model
-api_key_env: ` + environmentName + `
-`)},
-	}
-}
-
 func preparedSchemaSource() fstest.MapFS {
 	return fstest.MapFS{
 		"schema.json": &fstest.MapFile{Data: []byte(`{

profile_inheritance_contract_test.go

@@ -0,0 +1,243 @@
+package promptkit_test
+
+import (
+	"context"
+	"errors"
+	"io/fs"
+	"strings"
+	"sync"
+	"testing"
+	"testing/fstest"
+
+	"gitea.maximumdirect.net/eric/promptkit"
+)
+
+func TestProfileInheritanceBuiltInAliasWorkflow(t *testing.T) {
+	engine, err := promptkit.NewEngine(promptkit.Config{
+		PromptDir: frameworkPromptDir,
+		SchemaDir: frameworkSchemaDir,
+	}, promptkit.WithProfiles(promptkit.Profile{
+		ID:              "weather-light",
+		BaseProfileID:   "deepseek-4-flash",
+		ReasoningEffort: "high",
+		TimeoutSeconds:  120,
+	}))
+	if err != nil {
+		t.Fatalf("construct alias engine: %v", err)
+	}
+
+	base, err := engine.InspectProfile(context.Background(), "deepseek-4-flash")
+	if err != nil {
+		t.Fatalf("inspect base: %v", err)
+	}
+	child, err := engine.InspectProfile(context.Background(), "weather-light")
+	if err != nil {
+		t.Fatalf("inspect alias: %v", err)
+	}
+	if child.ProfileID != "weather-light" ||
+		child.EffectiveModelParams.BackendID != base.EffectiveModelParams.BackendID ||
+		child.EffectiveModelParams.Model != base.EffectiveModelParams.Model ||
+		child.EffectiveModelParams.ReasoningEffort != "high" ||
+		child.EffectiveModelParams.TimeoutSeconds != 120 {
+		t.Fatalf("alias inspection = %+v, base = %+v", child, base)
+	}
+
+	prepared, err := engine.Prepare(context.Background(), promptkit.RunRequest{
+		PromptID:  frameworkMarkdownSummaryPromptID,
+		ProfileID: "weather-light",
+		Inputs: map[string]promptkit.ArtifactRef{
+			"transcript": promptkit.Inline("Rin opens the gate."),
+			"glossary":   promptkit.Inline("gate: A guarded passage."),
+		},
+	})
+	if err != nil {
+		t.Fatalf("prepare alias: %v", err)
+	}
+	if prepared.SelectedProfileID != "weather-light" {
+		t.Fatalf("SelectedProfileID = %q", prepared.SelectedProfileID)
+	}
+
+	timeout := 15
+	reasoning := "low"
+	overridden, err := engine.Prepare(context.Background(), promptkit.RunRequest{
+		PromptID:  frameworkMarkdownSummaryPromptID,
+		ProfileID: "weather-light",
+		Execution: &promptkit.ExecutionTargetOverride{
+			TimeoutSeconds:  &timeout,
+			ReasoningEffort: &reasoning,
+		},
+		Inputs: map[string]promptkit.ArtifactRef{
+			"transcript": promptkit.Inline("Rin opens the gate."),
+			"glossary":   promptkit.Inline("gate: A guarded passage."),
+		},
+	})
+	if err != nil {
+		t.Fatalf("prepare override: %v", err)
+	}
+	if overridden.EffectiveModelParams.TimeoutSeconds != timeout ||
+		overridden.EffectiveModelParams.ReasoningEffort != reasoning {
+		t.Fatalf("runtime override target = %+v", overridden.EffectiveModelParams)
+	}
+}
+
+func TestProfileInheritanceYAMLAliasOfBuiltIn(t *testing.T) {
+	engine, err := promptkit.NewEngine(promptkit.Config{},
+		promptkit.WithPromptFS(fstest.MapFS{}, "."),
+		promptkit.WithProfileFS(fstest.MapFS{
+			"alias.yaml": &fstest.MapFile{Data: []byte("id: yaml-alias\nbase_profile: deepseek-4-flash\n")},
+		}, "."),
+	)
+	if err != nil {
+		t.Fatalf("construct YAML alias engine: %v", err)
+	}
+	inspection, err := engine.InspectProfile(context.Background(), "yaml-alias")
+	if err != nil {
+		t.Fatalf("inspect YAML alias: %v", err)
+	}
+	if inspection.ProfileID != "yaml-alias" || inspection.EffectiveModelParams.Model == "" {
+		t.Fatalf("YAML alias inspection = %+v", inspection)
+	}
+}
+
+func TestProfileInheritanceRetainsRequiredCredentialBehavior(t *testing.T) {
+	engine, err := promptkit.NewEngine(promptkit.Config{},
+		promptkit.WithPromptFS(fstest.MapFS{}, "."),
+		promptkit.WithBackend(promptkit.Backend{
+			ID:        "credential-backend",
+			Endpoint:  "https://credential.example/v1",
+			APIKeyEnv: "OPTIONAL_BACKEND_KEY",
+		}),
+		promptkit.WithProfiles(
+			promptkit.Profile{
+				ID:             "credential-base",
+				BackendID:      "credential-backend",
+				Model:          "model",
+				APIKeyRequired: true,
+			},
+			promptkit.Profile{ID: "credential-child", BaseProfileID: "credential-base"},
+		),
+	)
+	if err != nil {
+		t.Fatalf("construct credential inheritance engine: %v", err)
+	}
+	inspection, err := engine.InspectProfile(context.Background(), "credential-child")
+	if err != nil {
+		t.Fatalf("inspect credential child: %v", err)
+	}
+	if !inspection.APIKeyRequired || inspection.EffectiveModelParams.APIKeyEnv != "" {
+		t.Fatalf("credential inspection = %+v", inspection)
+	}
+}
+
+func TestProfileInheritancePreservesPublicErrorIdentities(t *testing.T) {
+	newEngine := func(t *testing.T, profiles fs.FS) *promptkit.Engine {
+		t.Helper()
+		options := []promptkit.Option{promptkit.WithPromptFS(fstest.MapFS{}, ".")}
+		if profiles != nil {
+			options = append(options, promptkit.WithProfileFS(profiles, "."))
+		}
+		engine, err := promptkit.NewEngine(promptkit.Config{}, options...)
+		if err != nil {
+			t.Fatalf("construct engine: %v", err)
+		}
+		return engine
+	}
+
+	tests := []struct {
+		name     string
+		profiles fs.FS
+		profile  string
+		contains []string
+		want     error
+		wantNot  error
+	}{
+		{
+			name:    "missing selected profile",
+			profile: "missing",
+			want:    promptkit.ErrProfileNotFound,
+			wantNot: promptkit.ErrProfileLoad,
+		},
+		{
+			name: "missing base",
+			profiles: fstest.MapFS{
+				"child.yaml": &fstest.MapFile{Data: []byte("id: child\nbase_profile: missing\n")},
+			},
+			profile:  "child",
+			contains: []string{"child", "missing"},
+			want:     promptkit.ErrProfileLoad,
+			wantNot:  promptkit.ErrProfileNotFound,
+		},
+		{
+			name: "cycle",
+			profiles: fstest.MapFS{
+				"a.yaml": &fstest.MapFile{Data: []byte("id: a\nbase_profile: b\n")},
+				"b.yaml": &fstest.MapFile{Data: []byte("id: b\nbase_profile: a\n")},
+			},
+			profile:  "a",
+			contains: []string{"a", "b"},
+			want:     promptkit.ErrProfileLoad,
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			result, err := newEngine(t, tc.profiles).InspectProfile(context.Background(), tc.profile)
+			if result != nil || !errors.Is(err, tc.want) || (tc.wantNot != nil && errors.Is(err, tc.wantNot)) {
+				t.Fatalf("inspection=(%+v, %v), want %v without %v", result, err, tc.want, tc.wantNot)
+			}
+			for _, fragment := range tc.contains {
+				if !strings.Contains(err.Error(), fragment) {
+					t.Fatalf("error = %v, want %q", err, fragment)
+				}
+			}
+		})
+	}
+}
+
+func TestProfileInheritanceFreezesPreparedExecution(t *testing.T) {
+	profiles := &mutableInheritanceProfileFS{files: fstest.MapFS{
+		"child.yaml": &fstest.MapFile{Data: []byte("id: child\nbase_profile: base\n")},
+		"base.yaml":  &fstest.MapFile{Data: []byte("id: base\nendpoint: https://base.example/v1\nmodel: first-model\n")},
+	}}
+	client := &fakeLLMClient{response: &promptkit.GenerateResponse{Content: "ok"}}
+	engine, err := promptkit.NewEngine(promptkit.Config{},
+		promptkit.WithPromptFS(contractPromptFS("prepared", "child", "content"), "."),
+		promptkit.WithProfileFS(profiles, "."),
+		promptkit.WithLLMClient(client),
+	)
+	if err != nil {
+		t.Fatalf("construct engine: %v", err)
+	}
+
+	prepared, err := engine.PrepareExecution(context.Background(), promptkit.RunRequest{PromptID: "prepared"})
+	if err != nil {
+		t.Fatalf("prepare execution: %v", err)
+	}
+	profiles.set("base.yaml", "id: base\nendpoint: https://base.example/v1\nmodel: second-model\n")
+
+	result, err := engine.RunPrepared(context.Background(), prepared)
+	if err != nil || result == nil || len(client.requests) != 1 || client.requests[0].Target.Model != "first-model" {
+		t.Fatalf("prepared execution=(%+v, %v), requests=%+v", result, err, client.requests)
+	}
+	inspection, err := engine.InspectProfile(context.Background(), "child")
+	if err != nil || inspection.EffectiveModelParams.Model != "second-model" {
+		t.Fatalf("fresh inspection=(%+v, %v)", inspection, err)
+	}
+}
+
+type mutableInheritanceProfileFS struct {
+	mu    sync.RWMutex
+	files fstest.MapFS
+}
+
+func (f *mutableInheritanceProfileFS) Open(name string) (fs.File, error) {
+	f.mu.RLock()
+	defer f.mu.RUnlock()
+	return f.files.Open(name)
+}
+
+func (f *mutableInheritanceProfileFS) set(name, content string) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	f.files[name] = &fstest.MapFile{Data: []byte(content)}
+}

profiles.go

@@ -2,17 +2,16 @@ package promptkit
 
 import (
 	"context"
-	"errors"
 	"fmt"
-	"strings"
 
 	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
 	"gitea.maximumdirect.net/eric/promptkit/internal/jsonvalue"
 	"gitea.maximumdirect.net/eric/promptkit/internal/profile"
 )
 
-// OpenAICompatibleProfile returns an ordinary in-memory Profile for an
+// OpenAICompatibleProfile returns an in-memory Profile for an OpenAI-compatible
-// OpenAI-compatible chat-completions endpoint.
+// chat-completions endpoint. A non-blank BaseProfileID permits its target
+// fields to be inherited when the profile is selected or inspected.
 //
 // It does not register global state, maintain a model catalog, or resolve
 // credentials. If APIKeyRequired is true, callers satisfy it with
@@ -25,6 +24,7 @@ import (
 func OpenAICompatibleProfile(cfg OpenAICompatibleProfileConfig) Profile {
 	return Profile{
 		ID:              cfg.ID,
+		BaseProfileID:   cfg.BaseProfileID,
 		BackendID:       cfg.BackendID,
 		Endpoint:        cfg.Endpoint,
 		Model:           cfg.Model,
@@ -87,8 +87,9 @@ func toDomainProfile(publicProfile Profile) (domain.ExecutionProfile, error) {
 		return domain.ExecutionProfile{}, err
 	}
 	prof := domain.ExecutionProfile{
-		ID:              strings.TrimSpace(publicProfile.ID),
+		ID:              publicProfile.ID,
-		BackendID:       strings.TrimSpace(publicProfile.BackendID),
+		BaseProfileID:   publicProfile.BaseProfileID,
+		BackendID:       publicProfile.BackendID,
 		Endpoint:        publicProfile.Endpoint,
 		Model:           publicProfile.Model,
 		Temperature:     publicProfile.Temperature,
@@ -100,34 +101,8 @@ func toDomainProfile(publicProfile Profile) (domain.ExecutionProfile, error) {
 		APIKeyRequired:  publicProfile.APIKeyRequired,
 		ExtraParams:     extraParams,
 	}
-	if err := normalizeAndValidatePublicProfile(&prof); err != nil {
+	if err := profile.NormalizeAndValidateDefinition(&prof); err != nil {
 		return domain.ExecutionProfile{}, err
 	}
 	return prof, nil
 }
-
-func normalizeAndValidatePublicProfile(prof *domain.ExecutionProfile) error {
-	if strings.TrimSpace(prof.ID) == "" {
-		return errors.New("id is required")
-	}
-	prof.Endpoint = strings.TrimSpace(prof.Endpoint)
-	if strings.TrimSpace(prof.BackendID) == "" && prof.Endpoint == "" {
-		return errors.New("backend or endpoint is required")
-	}
-	if prof.Endpoint != "" {
-		endpoint, err := domain.NormalizeOpenAICompatibleBaseEndpoint(prof.Endpoint)
-		if err != nil {
-			return err
-		}
-		prof.Endpoint = endpoint
-	}
-	if strings.TrimSpace(prof.Model) == "" {
-		return errors.New("model is required")
-	}
-	return domain.ValidateExecutionTargetSettings(domain.ExecutionTarget{
-		Temperature:    prof.Temperature,
-		MaxTokens:      prof.MaxTokens,
-		TopP:           prof.TopP,
-		TimeoutSeconds: prof.TimeoutSeconds,
-	})
-}

public_contract_test.go

@@ -844,7 +844,7 @@ func TestBackendExtraParamsAreDeeplyCopiedAtConstructionAndLookup(t *testing.T)
 	}
 }
 
-func TestEngineValidationIsSinglePass(t *testing.T) {
+func TestEngineValidationWithZeroRepairBudgetIsSinglePass(t *testing.T) {
 	client := &fakeLLMClient{
 		response: &promptkit.GenerateResponse{Content: "not-json"},
 	}
@@ -859,7 +859,7 @@ func TestEngineValidationIsSinglePass(t *testing.T) {
 		Validation: &promptkit.OutputContract{
 			Format:         promptkit.FormatJSON,
 			ValidationMode: promptkit.ValidationJSON,
-			RepairAttempts: 3,
+			RepairAttempts: 0,
 		},
 	})
 	if err != nil {
@@ -874,6 +874,87 @@ func TestEngineValidationIsSinglePass(t *testing.T) {
 	}
 }
 
+func TestEngineRunRepairsJSONSchemaOutput(t *testing.T) {
+	client := &fakeLLMClient{responses: []*promptkit.GenerateResponse{
+		{
+			Content: "{}",
+			Usage:   promptkit.TokenUsage{PromptTokens: 2, CompletionTokens: 3, TotalTokens: 5, CachedTokens: 7, CacheWriteTokens: 11},
+		},
+		{
+			Content: `{"events":[{"title":"Repaired event"}]}`,
+			Usage:   promptkit.TokenUsage{PromptTokens: 13, CompletionTokens: 17, TotalTokens: 19, CachedTokens: 23, CacheWriteTokens: 29},
+		},
+	}}
+	engine := newContractEngineWithOptions(t, frameworkSchemaDir, promptkit.WithLLMClient(client))
+
+	result, err := engine.Run(context.Background(), promptkit.RunRequest{
+		PromptID:  frameworkStructuredEventsPromptID,
+		SessionID: " repair-session ",
+		Inputs: map[string]promptkit.ArtifactRef{
+			"transcript": promptkit.Inline("Rin opens the gate."),
+			"glossary":   promptkit.Inline("gate: A guarded passage."),
+		},
+		Validation: &promptkit.OutputContract{
+			Format:         promptkit.FormatJSON,
+			ValidationMode: promptkit.ValidationJSONSchema,
+			SchemaPath:     "structured_events.schema.json",
+			RepairAttempts: 1,
+		},
+	})
+	if err != nil {
+		t.Fatalf("run: %v", err)
+	}
+	if result.RawOutput != client.responses[1].Content || result.Validation.Status != promptkit.ValidationPassed ||
+		result.Validation.RepairAttempts != 1 {
+		t.Fatalf("repaired result = %+v", result)
+	}
+	wantUsage := promptkit.TokenUsage{PromptTokens: 15, CompletionTokens: 20, TotalTokens: 24, CachedTokens: 30, CacheWriteTokens: 40}
+	if result.Usage != wantUsage {
+		t.Fatalf("usage = %+v, want %+v", result.Usage, wantUsage)
+	}
+	if len(client.requests) != 2 {
+		t.Fatalf("generation calls = %d, want 2", len(client.requests))
+	}
+	initial, repaired := client.requests[0], client.requests[1]
+	if initial.Prompt.SessionID != "repair-session" || repaired.Prompt.SessionID != initial.Prompt.SessionID ||
+		!reflect.DeepEqual(repaired.Target, initial.Target) || repaired.TargetPresence != initial.TargetPresence ||
+		!reflect.DeepEqual(repaired.StructuredOutput, initial.StructuredOutput) {
+		t.Fatalf("generation request state drifted: initial=%+v repaired=%+v", initial, repaired)
+	}
+	if initial.StructuredOutput == nil || initial.StructuredOutput.JSONSchema == nil {
+		t.Fatalf("expected structured output on initial request: %+v", initial)
+	}
+}
+
+func TestEngineRunReturnsFinalResultAfterRepairExhaustion(t *testing.T) {
+	client := &fakeLLMClient{responses: []*promptkit.GenerateResponse{
+		{Content: "not-json", Usage: promptkit.TokenUsage{PromptTokens: 2, CompletionTokens: 3, TotalTokens: 5}},
+		{Content: "still-not-json", Usage: promptkit.TokenUsage{PromptTokens: 7, CompletionTokens: 11, TotalTokens: 18}},
+	}}
+	engine := newContractEngineWithOptions(t, frameworkSchemaDir, promptkit.WithLLMClient(client))
+
+	result, err := engine.Run(context.Background(), promptkit.RunRequest{
+		PromptID: frameworkMarkdownSummaryPromptID,
+		Inputs: map[string]promptkit.ArtifactRef{
+			"transcript": promptkit.Inline("Rin opens the gate."),
+			"glossary":   promptkit.Inline("gate: A guarded passage."),
+		},
+		Validation: &promptkit.OutputContract{
+			Format:         promptkit.FormatJSON,
+			ValidationMode: promptkit.ValidationJSON,
+			RepairAttempts: 1,
+		},
+	})
+	if err != nil || result == nil {
+		t.Fatalf("run = (%+v, %v), want exhausted result", result, err)
+	}
+	if result.RawOutput != "still-not-json" || result.Validation.Status != promptkit.ValidationFailed ||
+		result.Validation.RepairAttempts != 1 || len(result.Validation.Errors) == 0 ||
+		result.Usage != (promptkit.TokenUsage{PromptTokens: 9, CompletionTokens: 14, TotalTokens: 23}) {
+		t.Fatalf("exhausted result = %+v", result)
+	}
+}
+
 func TestRepeatedOptionsUseLastValueInEachCategory(t *testing.T) {
 	profile := promptkit.Profile{ID: "profile", Endpoint: "http://example.test/v1", Model: "model"}
 

types.go

@@ -322,7 +322,10 @@ type ExecutionTarget struct {
 	// ReasoningEffort is the effective opaque provider-specific reasoning
 	// setting. An empty value instructs model clients to omit reasoning.
 	ReasoningEffort string `json:"reasoning_effort"`
-	// APIKeyEnv is an environment-variable name, not its credential value.
+	// APIKeyEnv is the resolved name of an optional environment lookup source,
+	// not its credential value. The built-in client omits Authorization when no
+	// usable direct or environment credential is available; injected clients may
+	// resolve this metadata differently.
 	APIKeyEnv string `json:"api_key_env"`
 	// ExtraParams contains copied JSON-compatible provider parameters.
 	ExtraParams map[string]any `json:"extra_params"`
@@ -426,9 +429,10 @@ type ExecutionTargetOverride struct {
 	// inherited value and disables reasoning for this run. Non-blank values
 	// are opaque and are not validated against a fixed vocabulary.
 	ReasoningEffort *string
-	// APIKeyEnv replaces the profile or backend environment-variable name when
+	// APIKeyEnv replaces the profile or backend optional environment lookup
-	// non-blank. A direct RunRequest.APIKey still takes precedence over
+	// source when non-blank. A direct RunRequest.APIKey still takes precedence.
-	// environment lookup.
+	// The built-in client omits Authorization when neither source has a usable
+	// value; injected clients may resolve this metadata differently.
 	APIKeyEnv string
 	// ExtraParams, when non-empty, replaces the complete profile or backend map.
 	// Values must be JSON-compatible: nil, booleans, finite numbers, strings,
@@ -439,31 +443,43 @@ type ExecutionTargetOverride struct {
 
 // Profile is an in-memory execution profile for library consumers.
 //
-// It is equivalent to a loaded profile file after validation. Raw API keys do
+// A standalone Profile is equivalent to a loaded profile file after local
-// not belong in profiles; use APIKeyRequired to require callers to provide a
+// validation. A derived profile names BaseProfileID and can inherit target
-// RunRequest.APIKey or explicit request ExecutionTargetOverride.APIKeyEnv, or
+// fields when selected or inspected. Raw API keys do not belong in profiles;
-// use profile YAML api_key_env with file and FS profile sources. Profile has no
+// use APIKeyRequired to require callers to provide a RunRequest.APIKey or
-// stable JSON representation.
+// explicit request ExecutionTargetOverride.APIKeyEnv, or use profile YAML
+// api_key_env with file and FS profile sources. Profile has no stable JSON
+// representation.
 //
-// WithProfiles validates and copies Profile values during NewEngine. Zero
+// WithProfiles locally validates and copies Profile values during NewEngine.
-// Temperature, MaxTokens, and TopP values and blank ServiceTier and
+// It checks base-reference existence and resolved target completeness when a
-// ReasoningEffort values leave those provider controls unspecified. A zero
+// derived profile is selected or inspected. Zero Temperature, MaxTokens, and
-// TimeoutSeconds retains the framework deadline, while an empty ExtraParams map
+// TopP values and blank ServiceTier and ReasoningEffort values leave those
-// inherits backend request defaults. Use ExecutionTargetOverride pointer fields
+// provider controls unspecified. A zero TimeoutSeconds retains the framework
-// to request an explicit numeric zero.
+// deadline, while an empty ExtraParams map inherits backend request defaults.
+// Use ExecutionTargetOverride pointer fields to request an explicit numeric
+// zero.
 type Profile struct {
 	// ID is the required non-blank profile identifier. WithProfiles trims it.
 	ID string
+	// BaseProfileID optionally names one base profile. WithProfiles trims it. A
+	// non-blank value permits required target fields to be inherited when the
+	// profile is selected or inspected, which is also when reference existence
+	// and resolved completeness are checked. A blank value leaves this as a
+	// standalone profile.
+	BaseProfileID string
 	// BackendID optionally selects an engine backend. WithProfiles trims it.
 	// Backend membership is checked when a request selects the profile; an
 	// unknown ID makes preparation fail with ErrProfileLoad.
 	BackendID string
-	// Endpoint is the model-provider base URL. It is required only when
+	// Endpoint is the model-provider base URL. A standalone Profile requires an
-	// BackendID is blank and otherwise overrides the backend endpoint when
+	// endpoint when BackendID is blank; a derived Profile may inherit either
+	// field. A non-blank endpoint overrides the backend endpoint when
 	// non-blank. WithProfiles trims it and requires an absolute HTTP or HTTPS URL
 	// with a host and no user information, query, or fragment.
 	Endpoint string
-	// Model is the required non-blank provider model identifier.
+	// Model is the provider model identifier. It is required for a standalone
+	// Profile and may be inherited by a derived Profile.
 	Model string
 	// Temperature is from 0 through 2. Zero leaves the provider control
 	// unspecified.
@@ -481,7 +497,8 @@ type Profile struct {
 	ReasoningEffort string
 	// APIKeyRequired clears a backend's inherited API-key environment name and
 	// requires a non-blank RunRequest.APIKey unless the request explicitly
-	// supplies ExecutionTargetOverride.APIKeyEnv. It does not store a credential.
+	// supplies ExecutionTargetOverride.APIKeyEnv. When false, a named
+	// environment source remains optional. It does not store a credential.
 	APIKeyRequired bool
 	// ExtraParams contains provider-specific JSON-compatible values. An empty
 	// map inherits backend request defaults, when any. WithProfiles validates
@@ -494,13 +511,16 @@ type Profile struct {
 // profile.
 //
 // It contains ordinary profile fields for OpenAI-compatible chat-completions
-// endpoints. APIKeyRequired follows Profile.APIKeyRequired. Raw API keys do not
+// endpoints. BaseProfileID and APIKeyRequired follow Profile. Raw API keys do
-// belong in this config. OpenAICompatibleProfileConfig has no stable JSON
+// not belong in this config. OpenAICompatibleProfileConfig has no stable JSON
 // representation and is not validated until its resulting Profile is supplied
 // through WithProfiles to NewEngine.
 type OpenAICompatibleProfileConfig struct {
 	// ID becomes Profile.ID.
 	ID string
+	// BaseProfileID becomes Profile.BaseProfileID. A non-blank value permits the
+	// resulting Profile to inherit target fields when it is selected or inspected.
+	BaseProfileID string
 	// BackendID becomes Profile.BackendID.
 	BackendID string
 	// Endpoint becomes Profile.Endpoint.
@@ -545,8 +565,8 @@ type ExecutionTargetPresence struct {
 // JSON representation.
 //
 // A non-nil RunRequest.Validation replaces the complete prompt contract. It
-// does not merge fields. The public Engine validates generated output once and
+// does not merge fields. The public Engine performs bounded correction after a
-// does not install an output repairer.
+// failed eligible validation when RepairAttempts is positive.
 type OutputContract struct {
 	// Format selects generated artifact metadata. An empty value in a non-nil
 	// request replacement defaults to FormatText.
@@ -557,9 +577,9 @@ type OutputContract struct {
 	// SchemaPath is required when ValidationMode is ValidationJSONSchema and is
 	// ignored by other modes.
 	SchemaPath string `json:"schema_path"`
-	// RepairAttempts is a non-negative requested repair limit. Zero requests no
+	// RepairAttempts is an additional generation-call budget from zero through
-	// repairs. The public Engine performs no repairs even when this value is
+	// three. Zero is single-pass. A positive value is valid only with basic,
-	// positive, so its runs report zero attempts used.
+	// json, or json_schema validation.
 	RepairAttempts int `json:"repair_attempts"`
 }
 
@@ -575,8 +595,8 @@ type ValidationResult struct {
 	Errors []string `json:"errors,omitempty"`
 	// SchemaPath is the effective schema path for JSON Schema validation.
 	SchemaPath string `json:"schema_path,omitempty"`
-	// RepairAttempts is the number of repairs actually attempted. It is always
+	// RepairAttempts is the number of corrective generation calls actually
-	// zero for the public Engine.
+	// started for this result.
 	RepairAttempts int `json:"repair_attempts"`
 	// IsValid is true for ValidationPassed and ValidationSkipped and false for
 	// ValidationFailed.
@@ -694,9 +714,8 @@ type GenerateRequest struct {
 // GenerateResponse is returned by an injected LLM client and has a stable JSON
 // representation.
 type GenerateResponse struct {
-	// Content is the generated output. It must be non-empty when using the
+	// Content is the generated output. It may be explicitly empty; Promptkit
-	// built-in client; injected clients may return empty content for Promptkit
+	// applies the effective output contract to classify it.
-	// validation to classify.
 	Content string `json:"content"`
 	// Usage is the client's token accounting.
 	Usage TokenUsage `json:"usage"`