diff --git a/docs/integrations/README.md b/docs/integrations/README.md
index ac3b456..a2192aa 100644
--- a/docs/integrations/README.md
+++ b/docs/integrations/README.md
@@ -1,15 +1,19 @@
-# Integration Documentation Index
+# Integrations Index
 
 ## Audience
-Developers and LLM coding agents changing Narratio's external integration contracts.
+Developers and coding agents changing Narratio's external integration boundaries.
 
 ## Scope
-Implemented-only reference notes for the external systems Narratio currently integrates with.
+`docs/integrations/` is the implementation-level reference for downstream tool adapter contracts.
 
-## Integration Docs
-- `audita.md`: Audita adapter invocation and validation contract.
-- `seriatim.md`: Seriatim normalize/merge/trim adapter contract.
-- `scriptorium.md`: Scriptorium run/render adapter contract.
+These docs cover what Narratio expects from external tools and what each adapter guarantees back to stage code.
 
-## Canonical Owner
-`docs/integrations/` is the canonical home for external integration reference notes per `docs/policy/documentation.md`.
+## Integration Contracts
+- `audita.md`: transcript polishing adapter (`audita process`).
+- `seriatim.md`: merge/normalize/trim adapter (`seriatim`).
+- `scriptorium.md`: artifact run/render adapter (`scriptorium run|render`).
+
+## Related Canonical Docs
+- `docs/config.md`: operator-facing configuration reference.
+- `docs/internal/adapters.md`: shared adapter boundary and runner wiring.
+- `docs/internal/stage-*.md`: stage-specific integration usage.
diff --git a/docs/integrations/audita.md b/docs/integrations/audita.md
index cbc4e13..6d57410 100644
--- a/docs/integrations/audita.md
+++ b/docs/integrations/audita.md
@@ -1,66 +1,60 @@
-# Integration: audita
+# Integration: Audita
 
 ## Purpose
-Define Narratio's adapter contract for transcript polishing via Audita CLI subprocess execution.
+Define the Audita adapter contract used by the `polish` stage.
 
-## Inputs and Outputs
-Inputs (`audita.PolishRequest`):
-- base transcript path
-- glossary path
-- output polished transcript path
-- optional report path (required when report enabled)
-- work dir
-- generated config path
-- stdout/stderr log paths
-- optional module/model/base URL and concurrency knobs
+## Adapter Boundary
+Interface:
+- `audita.Runner`
+- method: `Run(ctx, PolishRequest) (PolishResult, error)`
 
-Outputs (`audita.PolishResult`):
-- polished transcript path
-- optional report path
-- generated config path
-- stdout/stderr log paths
-- exit code, duration, invoked binary
-- adapter metadata
+Primary implementation:
+- `internal/adapters/audita/SubprocessRunner`
 
-## Boundaries
-Owns:
-- Deterministic CLI argument construction for `audita process`
-- Environment bridging for API credentials
-- Invocation config emission
-- Output validation for polished transcript and report
+Execution mode:
+- subprocess invocation of `audita process`
 
-Does not own:
-- Upstream/downstream stage orchestration
-- Credential sourcing policy beyond required env-var presence check
+## Request Contract
+`PolishRequest` carries:
+- required transcript/glossary/output/work-dir paths;
+- optional report path (required when report mode is enabled);
+- generated config and stdout/stderr log paths;
+- optional module/model/base-url/config/output-schema/concurrency settings.
 
-## Config Fields Used
-Via `pipeline.audita.*` mapped in app/stage wiring:
-- `binary`, `timeout`, `llm_api_key_env`, `modules`, `base_url`, `model`
-- `transcript_description`, `config_path`, `output_schema`, `work_dir_retention`
-- `total_llm_concurrency`, `proposal_llm_concurrency`, `validation_model`, `validation_llm_concurrency`, `report`
+## Result Contract
+`PolishResult` returns:
+- processed transcript path;
+- optional report path;
+- work dir and generated-config/log paths;
+- exit code, duration, binary provenance;
+- adapter metadata map.
 
-## External Adapters Used
-- Shared subprocess helper (`internal/adapters/subprocess`) to run CLI and capture logs.
+## Validation and Failure Semantics
+Construction fails for invalid static config values, including:
+- empty binary;
+- non-positive timeout;
+- invalid base URL;
+- invalid output schema;
+- invalid work-dir retention value;
+- invalid concurrency values.
 
-## State and Manifest Behavior
-- No direct manifest writes.
-- Stage-level metadata records adapter provenance and credential-present signal.
-- Generated invocation YAML is written when `GeneratedConfigPath` is provided.
+Run fails for:
+- missing required request paths;
+- missing required credential env var when configured (`llm_api_key_env`);
+- subprocess execution failure;
+- invalid processed transcript JSON (`segments` array required);
+- invalid report JSON when reporting is enabled.
 
-## Skip and Resume Behavior
-- Adapter has no skip/resume logic. Stage/runner controls this.
+Failure results still include output/log/config/exit metadata for diagnostics.
 
-## Failure Behavior
-- Constructor validation fails on invalid binary/timeout/schema/concurrency/URL values.
-- Run fails on missing required paths, missing required credential env var, subprocess errors, invalid polished JSON shape, or invalid report JSON.
-- Failures preserve stdout/stderr paths in returned result metadata.
+## Deterministic Behavior
+- CLI args are built from runner config + request in a fixed order.
+- Generated invocation YAML (`audita.generated.v1`) is emitted when requested.
+- Manifest writes are stage-owned; adapter itself is stateless.
 
-## Tests to Inspect Before Changing
-- `internal/adapters/audita/subprocess_test.go`
-- `internal/adapters/audita/fake_test.go`
-- `internal/stage/polish_test.go`
+## Config Mapping
+Config fields consumed through runner/stage wiring are under `pipeline.audita.*`.
 
-## Architectural Invariants
-- Polished output must be valid JSON with top-level `segments` array.
-- When report is enabled, report output must be valid JSON.
-- If `llm_api_key_env` is configured, credential must be present in environment.
+Maintained example with Audita config:
+- `examples/pipeline.full.annotated.yml`
+- `examples/pipeline.production.yml`
diff --git a/docs/integrations/scriptorium.md b/docs/integrations/scriptorium.md
index 76b16d6..599245b 100644
--- a/docs/integrations/scriptorium.md
+++ b/docs/integrations/scriptorium.md
@@ -1,64 +1,66 @@
-# Integration: scriptorium
+# Integration: Scriptorium
 
 ## Purpose
-Define Narratio's adapter contract for Scriptorium artifact generation and render-debug subprocess invocations.
+Define the Scriptorium adapter contract used by `analyze` and trim-bounds generation in `trim`.
 
-## Inputs and Outputs
-Inputs:
-- `RunArtifactRequest`: binary, config path, prompt/profile IDs, input map, vars map, timeout, output path, logs/config paths, optional API env and working dir
-- `RenderArtifactRequest`: same core fields for render mode
+## Adapter Boundary
+Interface:
+- `scriptorium.Runner`
+- methods:
+  - `RunArtifact(ctx, RunArtifactRequest)`
+  - `RenderArtifact(ctx, RenderArtifactRequest)`
 
-Outputs (`ArtifactResult`):
-- output path
-- stdout/stderr log paths
-- generated config path
-- exit code and duration
-- command mode (`run` or `render`)
-- prompt/profile provenance
-- validation failure signal
-- adapter metadata
+Primary implementation:
+- `internal/adapters/scriptorium/SubprocessRunner`
 
-## Boundaries
-Owns:
-- Deterministic CLI arg construction for `scriptorium run` and `scriptorium render`
-- Common request validation
-- Invocation config emission
-- Output existence/non-empty checks
-- Validation-failure mapping for run exit code 2
+Execution modes:
+- `scriptorium run`
+- `scriptorium render`
 
-Does not own:
-- Artifact selection policy (`analyze` stage)
-- Bounds semantic validation (`trim` stage)
+## Request Contract
+Both request types carry:
+- binary/config/prompt/profile IDs;
+- input map and vars map;
+- output path;
+- timeout;
+- generated config + stdout/stderr log paths;
+- optional API-key env var name;
+- optional working directory.
 
-## Config Fields Used
-Via `pipeline.scriptorium.*` and stage-level artifact config:
-- `binary`, `config_path`, `timeout`, `render_debug`
-- artifact-level `prompt_id`, `profile_id`, `timeout`, `inputs`, `vars`, `output_path`
+## Result Contract
+`ArtifactResult` returns:
+- output/log/generated-config paths;
+- exit code and duration;
+- command mode (`run` or `render`);
+- prompt/profile provenance;
+- `ValidationFailed` marker;
+- metadata map.
 
-## External Adapters Used
-- Shared subprocess helper (`internal/adapters/subprocess`).
+## Validation and Failure Semantics
+Request validation fails for:
+- missing binary, prompt id, or output path;
+- non-positive timeout;
+- empty input/var names;
+- empty input path values;
+- missing required credential env var when `APIKeyEnv` is set.
 
-## State and Manifest Behavior
-- No direct manifest writes.
-- Stage metadata records adapter outputs and command mode.
-- Generated invocation YAML is written when requested.
+Run behavior:
+- subprocess errors propagate with context;
+- `run` exit code `2` is mapped to `ValidationFailed=true`;
+- successful subprocess still fails if output file is missing or empty.
 
-## Skip and Resume Behavior
-- Adapter has no skip/resume logic. Stage/runner controls execution.
+Render behavior:
+- subprocess errors propagate;
+- output file must exist and be non-empty.
 
-## Failure Behavior
-- Request validation fails for missing binary/prompt/output, invalid timeout, invalid input/var names, or missing required API env var.
-- Subprocess errors bubble with command context.
-- `run` exit code 2 is treated as `ValidationFailed=true` and surfaced as error by calling stage.
-- Successful subprocess still fails if output file is missing/empty.
+## Deterministic Behavior
+- input and var maps are sorted into deterministic `--input` and `--var` CLI args.
+- generated invocation YAML (`scriptorium.generated.v1`) is emitted when requested.
+- adapter is stateless and does not own artifact-selection policy.
 
-## Tests to Inspect Before Changing
-- `internal/adapters/scriptorium/subprocess_test.go`
-- `internal/adapters/scriptorium/fake_test.go`
-- `internal/stage/analyze_test.go`
-- `internal/stage/trim_test.go`
+## Config Mapping
+Config fields consumed through runner/stage wiring are under `pipeline.scriptorium.*` plus per-artifact settings under `pipeline.scriptorium.artifacts.*`.
 
-## Architectural Invariants
-- Both modes require explicit timeout > 0.
-- Input/var maps are sorted into deterministic CLI argument order.
-- Run-mode validation failures are represented explicitly, not silently skipped.
+Maintained examples with Scriptorium config:
+- `examples/pipeline.full.annotated.yml`
+- `examples/pipeline.production.yml`
diff --git a/docs/integrations/seriatim.md b/docs/integrations/seriatim.md
index 279b98a..491c341 100644
--- a/docs/integrations/seriatim.md
+++ b/docs/integrations/seriatim.md
@@ -1,60 +1,56 @@
-# Integration: seriatim
+# Integration: Seriatim
 
 ## Purpose
-Define Narratio's adapter contract for merge, normalize, and trim subprocess invocations of Seriatim.
+Define the Seriatim adapter contract used by `merge`, `normalize`, and `trim`.
 
-## Inputs and Outputs
-Inputs:
-- `MergeRequest`: raw/per-speaker normalized transcript inputs, base output path, optional report, speaker/autocorrect paths, logs/config
-- `NormalizeRequest`: input transcript, output path, schema, optional report, timeout/log/config
-- `TrimRequest`: input transcript, output path, keep selector, timeout/log/config
+## Adapter Boundary
+Interface:
+- `seriatim.Runner`
+- methods:
+  - `Run(ctx, MergeRequest)`
+  - `Normalize(ctx, NormalizeRequest)`
+  - `Trim(ctx, TrimRequest)`
 
-Outputs:
-- `MergeResult`, `NormalizeResult`, `TrimResult` with output paths, logs/config paths, exit code, duration, binary provenance, and metadata.
+Primary implementation:
+- `internal/adapters/seriatim/SubprocessRunner`
 
-## Boundaries
-Owns:
-- Validated deterministic CLI invocation construction
-- Optional env tuning propagation for merge
-- Invocation config file emission
-- JSON output validation
+Execution modes:
+- `seriatim merge`
+- `seriatim normalize`
+- `seriatim trim`
 
-Does not own:
-- Transcript input selection/materialization logic (stage-owned)
-- Bounds computation (scriptorium/trim-stage-owned)
+## Request/Result Contracts
+- `MergeRequest`/`MergeResult`: multi-input merge to base transcript, optional report.
+- `NormalizeRequest`/`NormalizeResult`: transcript normalization with explicit schema.
+- `TrimRequest`/`TrimResult`: transcript trimming with required keep selector.
 
-## Config Fields Used
-Via `pipeline.seriatim.*` mapped in app/stage wiring:
-- `binary`, `timeout`, `output_schema`, `coalesce_gap`, `report`
-- `env.overlap_word_run_gap`
-- `env.overlap_word_run_reorder_window`
-- `env.backchannel_max_duration`
-- `env.filler_max_duration`
+Results include output/log/config paths, timing, exit code, and metadata.
 
-## External Adapters Used
-- Shared subprocess helper (`internal/adapters/subprocess`).
+## Validation and Failure Semantics
+Runner construction validates:
+- binary presence;
+- timeout > 0;
+- supported output schema (`seriatim-minimal|seriatim-intermediate|seriatim-full`);
+- non-negative coalesce gap.
 
-## State and Manifest Behavior
-- No direct manifest writes.
-- Stage metadata consumes adapter result fields and preserves generated config/log references.
+Invocation fails on:
+- missing required request paths/inputs;
+- invalid normalize schema override;
+- subprocess failure;
+- invalid JSON outputs;
+- missing `segments` array for normalize/trim transcript outputs.
 
-## Skip and Resume Behavior
-- Adapter has no skip/resume logic. Runner controls stage execution.
+When report paths are provided/enabled, report files must parse as JSON.
 
-## Failure Behavior
-- Constructor fails for invalid binary/timeout/output-schema/coalesce-gap.
-- Merge fails on missing output path/inputs/report path (if enabled), subprocess errors, invalid merged output JSON, invalid report JSON.
-- Normalize fails on missing input/output, invalid schema, subprocess errors, invalid final output JSON shape, invalid report JSON.
-- Trim fails on missing input/output/keep selector, subprocess errors, invalid final-trimmed output JSON shape.
+## Deterministic Behavior
+- argument ordering is deterministic per command construction.
+- merge env overrides are explicit (`SERIATIM_*`) and only emitted when configured.
+- generated invocation YAML (`seriatim.generated.v1`) is emitted when requested.
+- adapter does not write manifests or choose stage inputs.
 
-## Tests to Inspect Before Changing
-- `internal/adapters/seriatim/subprocess_test.go`
-- `internal/adapters/seriatim/fake_test.go`
-- `internal/stage/merge_test.go`
-- `internal/stage/normalize_test.go`
-- `internal/stage/trim_test.go`
+## Config Mapping
+Config fields consumed through runner/stage wiring are under `pipeline.seriatim.*`.
 
-## Architectural Invariants
-- Supported output schemas are limited to `seriatim-minimal`, `seriatim-intermediate`, `seriatim-full`.
-- Final and final-trimmed outputs must include `segments` arrays.
-- Merge/normalize/trim all route through deterministic subprocess invocation.
+Maintained examples with Seriatim config:
+- `examples/pipeline.full.annotated.yml`
+- `examples/pipeline.production.yml`