Expose pipeline LLM profile defaults

docs/cli.md

@@ -39,7 +39,7 @@ pipeline ID and **--input** are required.
 | **--debug** | Retain a debug bundle for this run. |
 | **--debug-dir path** | Override the debug-bundle root. Requires **--debug**. |
 | **--only lane-a,lane-b** | Run only the selected comma-separated artifact lanes when that selection is valid for the configured pipeline. |
-| **--llm-profile id** | Override effective LLM-capable module bindings with one configured profile. |
+| **--llm-profile id** | Highest-precedence configured profile for selected LLM-backed bindings and validators; it replaces binding and [pipeline](config.md#pipelines) defaults. |
 | **--session-id id** | Supply a non-empty prompt session identifier to LLM-backed module calls. |
 | **--reasoning-effort value** | Replace the selected PromptKit profile's reasoning effort for every LLM-backed call in this run. The value must be non-empty and the flag may be specified only once. |
 | **--clear-reasoning-effort** | Clear reasoning effort inherited from the selected PromptKit profile for every LLM-backed call in this run. |

docs/config.md

@@ -197,6 +197,7 @@ pipelines:
 
 | Field | Type | Default | Rules |
 | --- | --- | --- | --- |
+| **llm_profile** | string | none | Optional non-empty default PromptKit profile ID for selected LLM-backed bindings and validators. |
 | **input** | module binding | none | Required. |
 | **chunk** | module binding | **generic** | Optional. |
 | **output** | module binding | **json** | Optional. |
@@ -210,6 +211,11 @@ needs a unique non-empty **id**, an **artifacts** map, and may have
 **references**. A lane ID must not appear more than once in a pipeline,
 including across explicit steps.
 
+For each selected LLM-backed binding or validator, profile selection uses the
+run-level **--llm-profile** value first, then the binding's **llm_profile**,
+then the pipeline's **llm_profile**, and finally the PromptKit default.
+Deterministic bindings do not receive these defaults or run overrides.
+
 A lane has these fields:
 
 | Field | Type | Default | Rules |
@@ -246,7 +252,7 @@ extract:
 | Binding field | Type | Default | Rules |
 | --- | --- | --- | --- |
 | **module** | string | none | Required for an object binding. Must be a registered compatible key. |
-| **llm_profile** | string | none | Optional non-empty PromptKit profile ID. |
+| **llm_profile** | string | none | Optional non-empty PromptKit profile ID for an LLM-backed binding. It overrides the pipeline default unless the run supplies **--llm-profile**. |
 | **retries** | integer | 0 | Non-negative additional attempts for chunk, extract, merge, and normalize bindings. |
 | **options** | object | none | Must satisfy the selected module. |
 | **references** | map | none | Valid only on chunk, extract, merge, and normalize bindings. |
@@ -256,7 +262,8 @@ Omitting **validators** uses the registered chain. **validators: []** selects
 an empty chain; a non-empty list replaces the chain in the listed order.
 Validator bindings accept only **module**, **llm_profile**, and **options**.
 They reject **references**, **retries**, and nested **validators**. Deterministic
-validators reject an explicit **llm_profile**.
+validators reject an explicit **llm_profile**. Deterministic module bindings
+also reject an explicit **llm_profile**.
 
 The **json** output module accepts optional **include_chunk_map** and
 **evidence_context** settings:

internal/cli/command_contract_test.go

@@ -154,6 +154,23 @@ func TestConfigValidateResolvesPipelineAndChecksSelection(t *testing.T) {
 	}
 }
 
+func TestConfigValidatePipelineDefaultProfileIsOffline(t *testing.T) {
+	configPath := writeCommandConfigContent(t, `version: 4
+pipelines:
+  demo:
+    llm_profile: dnd-extraction
+    input: seriatim
+    artifacts:
+      spells:
+        extract: dnd/spells
+`)
+	var stdout, stderr bytes.Buffer
+	code := RunWithOptions([]string{"config", "validate", "--config", configPath, "--pipeline", "demo"}, &stdout, &stderr, Options{})
+	if code != 0 || !strings.Contains(stdout.String(), "valid for pipeline \"demo\"") || stderr.Len() != 0 {
+		t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
+	}
+}
+
 func TestPipelinesListSortsNormalizedIDsInTextAndJSON(t *testing.T) {
 	configPath := writeCommandConfig(t, " zeta ", "alpha")
 	options := commandContractOptions(t)

internal/cli/run.go

@@ -954,11 +954,22 @@ func effectiveLLMProfileIDs(resolved pipeline.ResolvedPipeline) []string {
 			seen[id] = struct{}{}
 		}
 	}
-	add(resolved.Chunk)
+	if resolved.InputExecutionClass == contracts.ExecutionClassLLMBacked {
+		add(resolved.Input)
+	}
+	if resolved.ChunkExecutionClass == contracts.ExecutionClassLLMBacked {
+		add(resolved.Chunk)
+	}
 	for _, lane := range resolved.AllArtifactLanes() {
-		add(lane.Extract)
-		add(lane.Merge)
-		add(lane.Normalize)
+		if lane.ExtractExecutionClass == contracts.ExecutionClassLLMBacked {
+			add(lane.Extract)
+		}
+		if lane.MergeExecutionClass == contracts.ExecutionClassLLMBacked {
+			add(lane.Merge)
+		}
+		if lane.NormalizeExecutionClass == contracts.ExecutionClassLLMBacked {
+			add(lane.Normalize)
+		}
 	}
 	for _, chain := range resolved.ValidatorChains {
 		for _, validator := range chain.Validators {
@@ -967,6 +978,9 @@ func effectiveLLMProfileIDs(resolved pipeline.ResolvedPipeline) []string {
 			}
 		}
 	}
+	if resolved.OutputExecutionClass == contracts.ExecutionClassLLMBacked {
+		add(resolved.Output)
+	}
 	ids := make([]string, 0, len(seen))
 	for id := range seen {
 		ids = append(ids, id)

internal/cli/run_contract_test.go

@@ -318,6 +318,24 @@ func TestRunLLMProfileOverrideAndValidationUseInjectedBoundaries(t *testing.T) {
 			t.Fatalf("code=%d stdout=%q stderr=%q factoryCalls=%d", code, stdout.String(), stderr.String(), factoryCalls)
 		}
 	})
+
+	t.Run("pipeline default is rejected before factory access", func(t *testing.T) {
+		roots := newStateTestRoots(t)
+		profileDir := writeRunContractProfiles(t, "configured-profile")
+		prependRunContractConfig(t, roots, fmt.Sprintf("promptkit:\n  profile_dir: %q\n", profileDir))
+		replaceStateTestConfigLine(t, roots.config, "  sample:\n", "  sample:\n    llm_profile: missing-profile\n")
+		factoryCalls := 0
+		opts := newStateTestHarness().options()
+		opts.LLMClientFactory = func(context.Context, config.Config, string, LLMRuntimeOverrides) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
+			factoryCalls++
+			return nil, nil, nil
+		}
+		var stdout, stderr bytes.Buffer
+		code := RunWithOptions([]string{"run", "sample", "--config", roots.config, "--input", roots.input, "--chunk_cache", "bypass"}, &stdout, &stderr, opts)
+		if code != 1 || !strings.Contains(stderr.String(), "not configured") || factoryCalls != 0 || stdout.Len() != 0 {
+			t.Fatalf("code=%d stdout=%q stderr=%q factoryCalls=%d", code, stdout.String(), stderr.String(), factoryCalls)
+		}
+	})
 }
 
 func TestRunReasoningEffortOverrideReachesFactory(t *testing.T) {
@@ -445,24 +463,30 @@ func TestReasoningEffortOverrideSeparatesCheckpointIdentities(t *testing.T) {
 
 func TestEffectiveLLMProfileIDsAreSortedDeduplicatedAndLLMOnly(t *testing.T) {
 	resolved := pipeline.ResolvedPipeline{
-		Input: pipeline.ModuleBinding{LLMProfile: "input-profile"},
-		Chunk: pipeline.ModuleBinding{LLMProfile: " zeta "},
+		Input:               pipeline.ModuleBinding{LLMProfile: "input-profile"},
+		InputExecutionClass: contracts.ExecutionClassLLMBacked,
+		Chunk:               pipeline.ModuleBinding{LLMProfile: " zeta "},
+		ChunkExecutionClass: contracts.ExecutionClassLLMBacked,
 		Steps: []pipeline.ResolvedPipelineStep{{
 			ID: "default",
 			ArtifactLanes: []pipeline.ResolvedArtifactLane{{
-				Extract:   pipeline.ModuleBinding{LLMProfile: "alpha"},
-				Merge:     pipeline.ModuleBinding{LLMProfile: "zeta"},
-				Normalize: pipeline.ModuleBinding{LLMProfile: " gamma "},
+				Extract:                 pipeline.ModuleBinding{LLMProfile: "alpha"},
+				ExtractExecutionClass:   contracts.ExecutionClassLLMBacked,
+				Merge:                   pipeline.ModuleBinding{LLMProfile: "deterministic-merge"},
+				MergeExecutionClass:     contracts.ExecutionClassDeterministic,
+				Normalize:               pipeline.ModuleBinding{LLMProfile: " gamma "},
+				NormalizeExecutionClass: contracts.ExecutionClassLLMBacked,
 			}},
 		}},
 		ValidatorChains: []pipeline.ResolvedValidatorChain{{Validators: []pipeline.ResolvedValidator{
 			{Binding: pipeline.ModuleBinding{LLMProfile: "deterministic-profile"}, ExecutionClass: contracts.ExecutionClassDeterministic},
 			{Binding: pipeline.ModuleBinding{LLMProfile: "beta"}, ExecutionClass: contracts.ExecutionClassLLMBacked},
 		}}},
-		Output: pipeline.ModuleBinding{LLMProfile: "output-profile"},
+		Output:               pipeline.ModuleBinding{LLMProfile: "output-profile"},
+		OutputExecutionClass: contracts.ExecutionClassLLMBacked,
 	}
 	got := effectiveLLMProfileIDs(resolved)
-	want := []string{"alpha", "beta", "gamma", "zeta"}
+	want := []string{"alpha", "beta", "gamma", "input-profile", "output-profile", "zeta"}
 	if strings.Join(got, ",") != strings.Join(want, ",") {
 		t.Fatalf("effective profiles = %#v, want %#v", got, want)
 	}

internal/core/config/effective_config_contract_test.go

@@ -242,6 +242,25 @@ func TestEffectiveConfigLLMProfileOverrideChangesDigestAndOverridesValidators(t
 	}
 }
 
+func TestEffectiveConfigPipelineLLMProfileIsInheritedWithoutMutatingConfig(t *testing.T) {
+	profile := effectiveProfile()
+	profile.LLMProfile = " configured-profile "
+	effective, err := resolveEffectiveProfile(t, profile, ResolveInput{})
+	if err != nil {
+		t.Fatalf("Resolve() error = %v", err)
+	}
+	if got := effective.Config.Pipelines["main"].LLMProfile; got != " configured-profile " {
+		t.Fatalf("effective config pipeline llm profile = %q, want preserved programmatic value", got)
+	}
+	resolved := effective.ResolvedPipeline
+	if got := resolved.Chunk.LLMProfile; got != "configured-profile" {
+		t.Fatalf("resolved chunk profile = %q, want inherited profile", got)
+	}
+	if got := resolved.Steps[0].ArtifactLanes[0].Extract.LLMProfile; got != "configured-profile" {
+		t.Fatalf("resolved extract profile = %q, want inherited profile", got)
+	}
+}
+
 func TestEffectiveConfigValidatorOverridesRemainDistinctAndOrdered(t *testing.T) {
 	tests := []struct {
 		name  string

internal/core/config/file_config.go

@@ -34,21 +34,23 @@ type FilePromptKitLocalBackendConfig struct {
 }
 
 type FilePipelineProfile struct {
-	Input        fileModuleBinding                  `yaml:"input"`
-	Chunk        *fileModuleBinding                 `yaml:"chunk,omitempty"`
-	Artifacts    map[string]FileArtifactLaneProfile `yaml:"artifacts,omitempty"`
-	Steps        []FilePipelineStepProfile          `yaml:"steps,omitempty"`
-	Output       *fileModuleBinding                 `yaml:"output,omitempty"`
-	References   map[string]fileReferenceSource     `yaml:"references,omitempty"`
-	artifactsSet bool                               `yaml:"-"`
-	stepsSet     bool                               `yaml:"-"`
+	LLMProfile    *string                            `yaml:"llm_profile,omitempty"`
+	Input         fileModuleBinding                  `yaml:"input"`
+	Chunk         *fileModuleBinding                 `yaml:"chunk,omitempty"`
+	Artifacts     map[string]FileArtifactLaneProfile `yaml:"artifacts,omitempty"`
+	Steps         []FilePipelineStepProfile          `yaml:"steps,omitempty"`
+	Output        *fileModuleBinding                 `yaml:"output,omitempty"`
+	References    map[string]fileReferenceSource     `yaml:"references,omitempty"`
+	artifactsSet  bool                               `yaml:"-"`
+	stepsSet      bool                               `yaml:"-"`
+	llmProfileSet bool                               `yaml:"-"`
 }
 
 func (p *FilePipelineProfile) UnmarshalYAML(node *yaml.Node) error {
 	type plainFilePipelineProfile FilePipelineProfile
 	var decoded plainFilePipelineProfile
 	seen, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
-		"input": {}, "chunk": {}, "artifacts": {}, "steps": {}, "output": {}, "references": {},
+		"llm_profile": {}, "input": {}, "chunk": {}, "artifacts": {}, "steps": {}, "output": {}, "references": {},
 	}, "pipeline profile")
 	if err != nil {
 		return err
@@ -56,6 +58,7 @@ func (p *FilePipelineProfile) UnmarshalYAML(node *yaml.Node) error {
 	*p = FilePipelineProfile(decoded)
 	_, p.artifactsSet = seen["artifacts"]
 	_, p.stepsSet = seen["steps"]
+	_, p.llmProfileSet = seen["llm_profile"]
 	return nil
 }
 
@@ -492,6 +495,13 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
 
 	for _, pipelineID := range pipelineIDs {
 		filePipeline := fileCfg.Pipelines[rawPipelineIDs[pipelineID]]
+		llmProfile := ""
+		if filePipeline.llmProfileSet || filePipeline.LLMProfile != nil {
+			if filePipeline.LLMProfile == nil || strings.TrimSpace(*filePipeline.LLMProfile) == "" {
+				return fmt.Errorf("pipeline %q llm_profile must not be empty when set", pipelineID)
+			}
+			llmProfile = strings.TrimSpace(*filePipeline.LLMProfile)
+		}
 		hasSteps := filePipeline.stepsSet || filePipeline.Steps != nil
 		laneIDs, rawLaneIDs, err := normalizedMapKeys(filePipeline.Artifacts, fmt.Sprintf("pipeline %q artifact lane id", pipelineID))
 		if err != nil {
@@ -499,6 +509,7 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
 		}
 		profile := pipeline.PipelineProfile{
 			ID:         pipelineID,
+			LLMProfile: llmProfile,
 			Input:      filePipeline.Input.toPipelineBinding(),
 			Artifacts:  make(map[string]pipeline.ArtifactLaneProfile, len(filePipeline.Artifacts)),
 			References: fileReferenceSourcesToPipeline(filePipeline.References),

internal/core/config/file_config_contract_test.go

@@ -2,6 +2,7 @@ package config
 
 import (
 	"encoding/json"
+	"fmt"
 	"os"
 	"path/filepath"
 	"reflect"
@@ -49,6 +50,72 @@ func TestFileConfigMinimalVersion4AppliesOverDefaults(t *testing.T) {
 	}
 }
 
+func TestFilePipelineLLMProfileIsPresenceAwareAndDetached(t *testing.T) {
+	const pipelineYAML = `version: 4
+pipelines:
+  main:
+    %s
+    input: input
+    artifacts:
+      lane:
+        extract: extract
+`
+
+	t.Run("omitted", func(t *testing.T) {
+		file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, ""))
+		if file.Pipelines["main"].LLMProfile != nil || file.Pipelines["main"].llmProfileSet {
+			t.Fatalf("parsed pipeline profile = %#v, want omitted llm profile", file.Pipelines["main"])
+		}
+		cfg := Default()
+		if err := cfg.ApplyFileConfig(file); err != nil {
+			t.Fatal(err)
+		}
+		if got := cfg.Pipelines["main"].LLMProfile; got != "" {
+			t.Fatalf("pipeline llm profile = %q, want empty", got)
+		}
+	})
+
+	t.Run("trimmed and detached", func(t *testing.T) {
+		file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "llm_profile: ' configured-profile '"))
+		cfg := Default()
+		if err := cfg.ApplyFileConfig(file); err != nil {
+			t.Fatal(err)
+		}
+		if got := cfg.Pipelines["main"].LLMProfile; got != "configured-profile" {
+			t.Fatalf("pipeline llm profile = %q, want trimmed value", got)
+		}
+		*file.Pipelines["main"].LLMProfile = "changed-profile"
+		if got := cfg.Pipelines["main"].LLMProfile; got != "configured-profile" {
+			t.Fatalf("effective config aliases parsed file: %q", got)
+		}
+		if got := cloneConfig(cfg).Pipelines["main"].LLMProfile; got != "configured-profile" {
+			t.Fatalf("cloned pipeline llm profile = %q", got)
+		}
+		data, err := json.Marshal(cfg)
+		if err != nil {
+			t.Fatal(err)
+		}
+		var roundTripped Config
+		if err := json.Unmarshal(data, &roundTripped); err != nil {
+			t.Fatal(err)
+		}
+		if got := roundTripped.Pipelines["main"].LLMProfile; got != "configured-profile" {
+			t.Fatalf("round-tripped pipeline llm profile = %q", got)
+		}
+	})
+
+	for _, value := range []string{"''", "'   '", "null"} {
+		t.Run("explicit empty "+value, func(t *testing.T) {
+			file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "llm_profile: "+value))
+			cfg := Default()
+			err := cfg.ApplyFileConfig(file)
+			if err == nil || !strings.Contains(err.Error(), `pipeline "main" llm_profile must not be empty`) {
+				t.Fatalf("ApplyFileConfig() error = %v, want explicit-empty rejection", err)
+			}
+		})
+	}
+}
+
 func TestFilePromptKitProfileSourcesSurviveConfigBoundaries(t *testing.T) {
 	tests := []struct {
 		name string