Add merge references and retry config

docs/internal/llm.md

@@ -41,6 +41,10 @@ The runtime records the actual selected Scriptorium profile, provider, and model
 used during execution. Manifest population does not rely on a precomputed
 profile ID before pipeline execution.
 
+Explicit profile validation and `--llm-profile` overrides apply to LLM-capable
+pipeline stages: chunk, extract, merge, and normalize. Input, output, and
+validator bindings are not part of the current production LLM profile scope.
+
 ## Scriptorium Adapter
 
 `ScriptoriumClient` implements `contracts.StructuredLLMClient` by converting

docs/internal/modules.md

@@ -20,7 +20,7 @@ A production module package should provide:
 Module specs should describe capabilities accurately. Resolution uses specs to
 reject incompatible pipelines before execution.
 
-Chunk, extract, and normalize modules that accept auxiliary reference material
+Chunk, extract, merge, and normalize modules that accept auxiliary reference material
 must declare slots through both `ReferenceSlots()` and
 `ModuleSpec().ReferenceSlots`. The runtime slot list and registry metadata
 should match so config validation can inspect slots without constructing module
@@ -31,10 +31,10 @@ must still be UTF-8 text. When a slot declares accepted media types, Notarius
 compares the canonical base media type inferred from the file extension,
 case-insensitively and without parameters.
 
-The resolver materializes reference content for chunk, extractor, and
+The resolver materializes reference content for chunk, extractor, merger, and
 normalizer targets. Runtime delivery uses `contracts.ChunkRequest.References`,
-`contracts.ExtractionRequest.References`, and
-`contracts.NormalizeRequest.References`. Reference material is not source
+`contracts.ExtractionRequest.References`, `contracts.MergeRequest.References`,
+and `contracts.NormalizeRequest.References`. Reference material is not source
 evidence and must not be converted into `SourceRef` values. If a module prompt
 uses references, pass them as prompt input materials through the structured LLM
 request. Prompt metadata hashes remain based on prompt asset source, not
@@ -48,7 +48,7 @@ Common D&D prompt fragments, reference slot helpers, prompt input assembly, and
 reference rendering live under `internal/modules/sharedassets/dnd`. Module
 contracts should expose prompt IDs, versions, input material names, and
 non-secret prompt/schema hashes through manifest metadata; they should not
-expose Scriptorium public types through chunk, extract, or normalize contracts.
+expose Scriptorium public types through chunk, extract, merge, or normalize contracts.
 
 Chunk modules receive the structured LLM client, configured Scriptorium profile
 ID, prompt session ID, and raw source input material through
@@ -60,6 +60,10 @@ Normalize modules receive the structured LLM client, configured Scriptorium
 profile ID, prompt session ID, and reference material through
 `contracts.NormalizeRequest` when they need model-backed reconciliation.
 
+Merge modules receive the structured LLM client, configured Scriptorium profile
+ID, prompt session ID, raw source input material, and reference material through
+`contracts.MergeRequest` when they need model-backed merge behavior.
+
 ## `seriatim` Input
 
 Package: `internal/modules/input/seriatim`

docs/internal/pipeline.md

@@ -33,18 +33,19 @@ The CLI writes the resolved pipeline and digest to diagnostics.
 
 Pipeline profiles and artifact lanes may include reference binding maps keyed by
 reference slot name. During resolution, pipeline-level bindings act as defaults
-for selected chunk, extractor, and normalizer targets that declare the slot;
-target-local bindings override or add bindings for that target. Runtime
+for selected chunk, extractor, merger, and normalizer targets that declare the
+slot; target-local bindings override or add bindings for that target. Runtime
 `--reference` requests override target config bindings, and runtime unbinds
 remove optional target bindings. Flat runtime slot names are resolved only when
 exactly one selected target declares the slot; otherwise the CLI requires a more
-specific selector such as `chunk.slot`, `lane.extract.slot`, or
-`lane.normalize.slot`. Resolution validates bindings against the declaring
-target specs and stores the bindings in target-aware resolved reference holders.
-It does not read reference files or include reference bytes in source digests.
+specific selector such as `chunk.slot`, `lane.extract.slot`,
+`lane.merge.slot`, or `lane.normalize.slot`. Resolution validates bindings
+against the declaring target specs and stores the bindings in target-aware
+resolved reference holders. It does not read reference files or include
+reference bytes in source digests.
 
-During run preparation, resolved file references for chunk, extractor, and
-normalizer targets are materialized before any LLM-backed pipeline work. Config
+During run preparation, resolved file references for chunk, extractor, merger,
+and normalizer targets are materialized before any LLM-backed pipeline work. Config
 bindings resolve relative to the config file, and CLI bindings resolve relative
 to the current working directory. Materialization accepts UTF-8 text files,
 computes `sha256:` content digests, records file origins, infers canonical base
@@ -55,8 +56,8 @@ empty bound files. Media-type acceptance is checked only when a slot declares
 manifests. The CLI writes provenance-only resolved reference diagnostics, and
 the run manifest records target-stage reference provenance separately from
 source digests. Runtime reference content is passed to the matching chunker,
-extractor, or normalizer request. LLM-backed modules pass that material onward
-as named Scriptorium prompt inputs.
+extractor, merger, or normalizer request. LLM-backed modules pass that material
+onward as named Scriptorium prompt inputs.
 
 The CLI carries raw input bytes into `pipeline.RunInput`. Input adapters parse
 those bytes into the source document, while LLM-backed modules that need the
@@ -65,9 +66,9 @@ origin metadata. The raw input payload is not written to manifests or default
 diagnostics.
 
 The CLI also carries an optional run `session_id`. The runner makes it available
-to chunk, extract, and normalize requests; LLM-backed modules forward it through
-their structured completion requests so Scriptorium can include it in prompt
-execution metadata.
+to chunk, extract, merge, and normalize requests; LLM-backed modules forward it
+through their structured completion requests so Scriptorium can include it in
+prompt execution metadata.
 
 ## Registries And Module Specs
 
@@ -83,10 +84,9 @@ Every production module registers a `ModuleSpec` with:
 - `Provides`: capabilities added after that module runs;
 - `Requires`: capabilities that must already be available.
 
-Chunk, extract, and normalize specs may also declare reference slots. Slot
+Chunk, extract, merge, and normalize specs may also declare reference slots. Slot
 declarations are available from registry metadata without constructing module
-instances. Input, merge, validate, and output specs must not declare reference
-slots.
+instances. Input, validate, and output specs must not declare reference slots.
 
 Capability checks prevent incompatible pipeline composition before a run starts.