Cleanup pass to remove refactoring-related artifacts and references

.gitignore

@@ -45,6 +45,17 @@ go.work.sum
 narratio
 local-test
 pipeline.yml
+bin/
+
+# Local run artifacts
+.audita-runs/
+report.json
+corrected.json
+normalized.json
+
+# Coverage artifacts
+coverage.out
+coverage.txt
 
 # ---> VisualStudioCode
 .vscode/*
@@ -59,4 +70,3 @@ pipeline.yml
 
 # Built Visual Studio Code Extensions
 *.vsix
-

README.md

@@ -1,28 +1,27 @@
-# Audita (Go)
+# Audita
 
 Audita is a transcript polishing CLI.
 
-The Go implementation in this repository is the active implementation. It runs a full default correction pipeline over transcript JSON using glossary context, LLM-backed proposal generation, validator chains, deterministic proposal application, and structured reports/diagnostics.
+`audita process` validates transcript/glossary input, normalizes and chunks transcript segments, runs the default correction pipeline, and emits corrected transcript output plus machine-readable diagnostics and reports.
 
-## What Audita does
+## What Audita Does
 
-`audita process` performs:
+Default module sequence:
-- transcript/glossary schema validation;
+- `glossary`
-- deterministic normalization and chunking;
+- `homophones`
-- default module sequence:
+- `glossary`
-  - `glossary`
+- `spoken_word`
-  - `homophones`
+- `grammar`
-  - `glossary`
-  - `spoken_word`
-  - `grammar`
-- glossary-backed domain/acoustic corrections;
-- conservative homophone and likely mistranscription corrections;
-- conservative spoken-word cleanup (dysfluencies/fillers) with semantic guardrails;
-- grammar/punctuation/capitalization/formatting cleanup;
-- machine-readable process and module reports;
-- per-run diagnostics artifacts with secret redaction.
 
-## Build and install
+Pipeline behavior includes:
+- glossary-backed domain/acoustic corrections
+- conservative homophone and mistranscription corrections
+- conservative spoken-word dysfluency cleanup with semantic guardrails
+- grammar/punctuation/capitalization/formatting cleanup
+- validator-chain enforcement before application
+- run reports and diagnostics artifacts with secret redaction
+
+## Build and Install
 
 Build a local binary:
 
@@ -36,7 +35,7 @@ Install into your Go bin directory:
 go install ./cmd/audita
 ```
 
-Run help:
+CLI help:
 
 ```sh
 audita --help
@@ -45,21 +44,19 @@ audita process --help
 
 ## Test
 
-Run the full test suite:
+Run all tests:
 
 ```sh
 go test ./...
 ```
 
-Normal tests are deterministic and do not require real LLM credentials or Python dependencies.
+## Basic Usage
-
-## Basic usage
 
 Required inputs:
 - transcript JSON path (positional argument)
 - `--glossary <glossary.yaml>`
 
-Default full pipeline (recommended local example):
+Recommended run:
 
 ```sh
 audita process transcript.json \
@@ -78,13 +75,13 @@ audita process transcript.json \
   --report-json report.json
 ```
 
-Emit transcript JSON to stdout (no `--output`):
+Write transcript JSON to stdout (no `--output`):
 
 ```sh
 audita process transcript.json --glossary glossary.yaml
 ```
 
-Diagnostics/work-dir control:
+Control diagnostics location/retention:
 
 ```sh
 audita process transcript.json \
@@ -95,17 +92,14 @@ audita process transcript.json \
   --report-json report.json
 ```
 
-## Stdout/stderr and orchestration behavior
+## Stdout/Stderr Contract
 
-- With `--output`, stdout should be empty on success.
+- With `--output`, stdout is expected to be empty on success.
 - Without `--output`, stdout contains transcript JSON only on success.
-- `--report-json` writes report JSON to file; report JSON is never printed to stdout.
+- `--report-json` writes a file and is never printed to stdout.
-- stderr is for human-readable warnings/errors.
+- stderr is human-readable diagnostics/errors.
 
-For parent-process integration guidance, see:
+For subprocess orchestration guidance, see [`docs/subprocess-operations.md`](docs/subprocess-operations.md).
-- [`docs/subprocess-operations.md`](docs/subprocess-operations.md)
-
-For orchestrated runs, use both `--output` and `--report-json`.
 
 ## Configuration
 
@@ -114,13 +108,14 @@ Precedence:
 2. environment (`AUDITA_*`)
 3. CLI flags
 
-### Module sequence
+### Modules
 
-- `AUDITA_MODULES` (CSV, e.g. `glossary,homophones,glossary,spoken_word,grammar`)
+- `AUDITA_MODULES` (CSV)
-- CLI override: `--modules`
+- CLI: `--modules`
 
-### Primary LLM settings
+### Primary LLM
 
+Environment:
 - `AUDITA_LLM_API_KEY` (or `OPENROUTER_API_KEY` fallback)
 - `AUDITA_MODEL`
 - `AUDITA_BASE_URL`
@@ -128,15 +123,17 @@ Precedence:
 - `AUDITA_MAX_RETRIES`
 - `AUDITA_LLM_CONCURRENCY`
 
-CLI overrides:
+CLI:
 - `--llm-api-key`
 - `--model`
 - `--base-url`
 - `--llm-timeout-seconds`
 - `--max-retries`
+- `--llm-concurrency`
 
-### Validation LLM settings
+### Validation LLM
 
+Environment:
 - `AUDITA_VALIDATION_LLM_API_KEY`
 - `AUDITA_VALIDATION_MODEL`
 - `AUDITA_VALIDATION_BASE_URL`
@@ -145,7 +142,7 @@ CLI overrides:
 - `AUDITA_VALIDATION_LLM_CONCURRENCY`
 - `AUDITA_VALIDATION_MAX_PROMPT_TOKENS`
 
-CLI overrides:
+CLI:
 - `--validation-llm-api-key`
 - `--validation-model`
 - `--validation-base-url`
@@ -154,25 +151,27 @@ CLI overrides:
 - `--validation-llm-concurrency`
 - `--validation-max-prompt-tokens`
 
-Validation LLM inheritance behavior:
+Validation concurrency behavior:
-- unset validation fields inherit from primary LLM config;
+- when validation concurrency is unset, it inherits primary `llm-concurrency`
-- set validation fields override primary values for validation calls only.
+- when explicitly set, validation concurrency must be `<= llm-concurrency`
 
-### Confidence thresholds
+### Confidence Thresholds
 
+Environment:
 - `AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD`
 - `AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD`
 - `AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD`
 - `AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD`
 
-CLI overrides:
+CLI:
 - `--glossary-confidence-threshold`
 - `--homophones-confidence-threshold`
 - `--spoken-word-confidence-threshold`
 - `--grammar-confidence-threshold`
 
-### Normalization and chunking
+### Normalization and Chunking
 
+Environment:
 - `AUDITA_NORMALIZE_MAX_SEGMENT_GAP`
 - `AUDITA_NORMALIZE_ELLIPSIS_GAP`
 - `AUDITA_NORMALIZE_MAX_SEGMENT_DURATION`
@@ -181,7 +180,7 @@ CLI overrides:
 - `AUDITA_MIN_SECTION_TOKENS`
 - `AUDITA_TARGET_SECTIONS`
 
-CLI overrides:
+CLI:
 - `--normalize-max-segment-gap`
 - `--normalize-ellipsis-gap`
 - `--normalize-max-segment-duration`
@@ -190,46 +189,38 @@ CLI overrides:
 - `--min-section-tokens`
 - `--target-sections`
 
-### Work-dir and retention
+### Work Directory
 
+Environment:
 - `AUDITA_WORK_DIR`
 - `AUDITA_WORK_DIR_RETENTION` (`auto`, `always`, `never`)
 
-CLI overrides:
+CLI:
 - `--work-dir`
 - `--work-dir-retention`
 
-Retention summary:
+Retention behavior:
-- `always`: keep all run directories.
+- `always`: keep all run directories
-- `never`: keep successful run directories.
+- `never`: keep successful run directories
-- `auto`: keep failed runs and successful runs with skipped/rejected corrections.
+- `auto`: keep failed runs and successful runs with skipped/rejected corrections
 
-## Report and diagnostics
+## Reports and Diagnostics
 
 Per-run diagnostics include:
-- source transcript artifacts;
+- source transcript artifacts
-- normalized transcript artifact;
+- normalized transcript artifact
-- normalization summary;
+- normalization summary
-- chunking summary;
+- chunking summary
-- invocation metadata;
+- invocation metadata
-- redacted effective config;
+- redacted effective config
-- prompt/response diagnostics for module and validator LLM interactions;
+- module/validator prompt-response diagnostics
-- `report.json`;
+- `report.json`
-- `error.log` on failure.
+- `error.log` on failure
 
 Optional external report output:
 - `--report-json <path>`
 
-## Legacy Python reference
+## Documentation
-
-The original Python implementation is preserved in [`python/`](python/) as a legacy/reference implementation for parity history and migration context.
-For migration guidance, see [`docs/migration-from-python.md`](docs/migration-from-python.md).
-
-Parity fixture notes and intentional differences:
-- [`docs/python-parity.md`](docs/python-parity.md)
-
-## Additional docs
 
 - Architecture: [`docs/architecture.md`](docs/architecture.md)
-- Rewrite history and phase notes: [`docs/rewrite-notes.md`](docs/rewrite-notes.md)
+- Subprocess operations: [`docs/subprocess-operations.md`](docs/subprocess-operations.md)
-- Migration from Python to Go: [`docs/migration-from-python.md`](docs/migration-from-python.md)

cmd/audita/main_integration_test.go

@@ -312,7 +312,7 @@ func TestProcessSuccessReportJSONSubprocess(t *testing.T) {
 		t.Fatalf("expected valid report JSON, got %q", string(report))
 	}
 	// Ensure report JSON is not printed to stdout.
-	if strings.Contains(result.stdout, `"phase16-default-pipeline-integration"`) {
+	if strings.Contains(result.stdout, `"default_pipeline"`) {
 		t.Fatalf("report JSON leaked to stdout: %q", result.stdout)
 	}
 }
@@ -493,7 +493,7 @@ func TestProcessCancellationViaSubprocessTimeoutHook(t *testing.T) {
 }
 
 func TestProcessSubprocessNoSecretLeakInOutputsAndDiagnostics(t *testing.T) {
-	secret := "phase18-subprocess-secret"
+	secret := "subprocess-secret"
 	workDir := t.TempDir()
 	reportPath := filepath.Join(t.TempDir(), "report.json")
 	outputPath := filepath.Join(t.TempDir(), "out.json")

docs/architecture.md

@@ -1,11 +1,10 @@
-# Audita Go Architecture
+# Audita Architecture
 
 ## Scope and intent
 This document describes:
-- the implemented Go architecture used in production today; and
+- the architecture used in production today.
-- historical rewrite-phase context that explains how the architecture was delivered.
 
-Status labels are explicit so future engineers and LLM agents do not infer missing behavior that is not actually missing.
+Historical rewrite details live in `docs/rewrite-notes.md`.
 
 ## Current implementation status
 Implemented today:
@@ -14,7 +13,7 @@ Implemented today:
 - Transcript and glossary parsing/validation.
 - Deterministic transcript normalization.
 - Deterministic token estimation and transcript chunking.
-- Per-run diagnostics directory creation plus Phase 6 process-level artifacts.
+- Per-run diagnostics directory creation plus process-level artifacts.
 - Process report JSON output with diagnostics artifact references.
 - Framework foundation packages for contracts and proposal application.
 - Production runner orchestration package with deterministic sequential module execution.
@@ -32,7 +31,7 @@ Implemented today:
 - Shared LLM proposal-generation helper with structured correction-set parsing.
 - Deterministic proposal-index assignment and enriched proposal mapping for shared generation.
 - Proposal-generation diagnostics artifacts with secret redaction.
-- Production module registry scaffolding with known-key recognition and explicit unsupported/unimplemented errors.
+- Production module registry with known-key recognition and explicit unsupported-module errors.
 - Production `grammar` module implementation in `internal/modules/grammar`.
 - Production `glossary` module implementation in `internal/modules/glossary`.
 - Production `homophones` module implementation in `internal/modules/homophones`.
@@ -52,19 +51,6 @@ Current reality:
   - `grammar`
 - repeated glossary stages are deterministic and reported distinctly as `glossary_1` and `glossary_2`.
 
-Phase sequencing note:
-- Phase 9 LLM infrastructure is complete (structured client, scheduler, effective config resolution, diagnostics primitives);
-- Phase 10 LLM-backed validator runtime integration is complete;
-- Phase 11 shared proposal-generation framework and module-registry scaffolding are complete;
-- Phase 12 grammar module implementation and explicit runtime wiring are complete;
-- Phase 13 glossary module and protected-term behavior are complete;
-- Phase 14 homophones module implementation and explicit runtime wiring are complete;
-- Phase 15 spoken-word module implementation and explicit runtime wiring are complete;
-- Phase 16 default full pipeline integration is complete;
-- Phase 17 parity fixture suite is complete;
-- Phase 18 operational hardening and subprocess integration are complete;
-- Phase 19 documentation/rollout completion is complete.
-
 ## Actual Go package layout
 
 ```text
@@ -177,7 +163,7 @@ Current runtime flow (`internal/cli/run.go`):
     - explicit `--modules` overrides the default sequence;
     - test/injected module factory path remains available for deterministic runtime tests.
 13. Output working transcript to `--output` file or stdout.
-14. Build process report (`phase` currently set to `phase16-default-pipeline-integration`).
+14. Build process report (`phase` currently set to `default_pipeline`).
 15. Optionally write `--report-json`; always write run-dir `report.json`.
 16. Apply work-dir retention.
 
@@ -290,7 +276,7 @@ Current behavior details:
 - section balancing is deterministic but heuristic.
 
 ## Implemented proposal/replacement infrastructure
-`internal/framework/proposals` provides deterministic foundation logic:
+`internal/framework/proposals` provides deterministic proposal composition logic:
 - `CorrectionProposal` and `EnrichedCorrectionProposal` models;
 - replacement policies: `require_unique`, `replace_all`;
 - safe preview (`PreviewProposalForSegment`) with stable skip reasons;
@@ -362,7 +348,7 @@ This helper only produces candidate proposals; validator-chain execution and pro
   - proposal/validation structured LLM clients
   - proposal/validation schedulers
   - diagnostics directory context
-- returns explicit errors for unknown keys (`unsupported_module`) and recognized-but-unimplemented keys (`unimplemented_module`).
+- returns explicit errors for unknown keys (`unsupported_module`).
 
 The `grammar`, `glossary`, `homophones`, and `spoken_word` module keys are now registered and constructible.
 
@@ -372,7 +358,7 @@ The `grammar`, `glossary`, `homophones`, and `spoken_word` module keys are now r
 - explicit guardrails against meaning-changing rewrites, style rewrites, summarization, and invention;
 - proposal generation through `internal/framework/proposal_generation` and `contracts.StructuredLLMClient`;
 - scheduler-aware proposal calls through existing `contracts.LLMScheduler` hooks;
-- replacement policy `require_unique` (matching Python implementation);
+- replacement policy `require_unique` (current runtime policy);
 - validator chain integration using existing deterministic + LLM-backed validators;
 - grammar confidence threshold enforcement through existing validator/config infrastructure;
 - module-level reporting and diagnostics capture through existing runner/reporting paths.
@@ -465,9 +451,6 @@ Current runtime note:
 - default non-explicit runs usually have no module-level skipped corrections, so `auto` commonly removes clean successful run directories.
 - explicit grammar/glossary/homophones/spoken_word runs can produce validator rejections and application skips, which are reflected in reports and retention input.
 
-Phase note:
-- Earlier-phase documentation deferred module and LLM prompt work; those deferred items were completed by Phases 12-16.
-
 ## Current tests and quality posture
 Implemented tests currently cover:
 - CLI argument handling and behavior (`internal/cli/run_test.go`)
@@ -483,7 +466,7 @@ Implemented tests currently cover:
 - validator models, cardinality enforcement, and deterministic validators (`internal/framework/validators/*_test.go`)
 - LLM-backed validator batching, prompt builders, structured-response safety, scheduler hooks, and diagnostics redaction (`internal/framework/validators/*_test.go`, `internal/framework/runner/*_test.go`)
 - shared proposal-generation request/response parsing, deterministic indexing, scheduler hooks, and diagnostics redaction (`internal/framework/proposal_generation/*_test.go`, `internal/framework/runner/*_test.go`)
-- production module-registry known-key recognition and unsupported/unimplemented error behavior (`internal/framework/modules/*_test.go`, `internal/cli/run_test.go`)
+- production module-registry known-key recognition and unsupported/internal-registry error behavior (`internal/framework/modules/*_test.go`, `internal/cli/run_test.go`)
 - production grammar module prompt constraints, proposal mapping, validator-chain behavior, confidence-threshold enforcement, diagnostics redaction, and explicit CLI/runtime integration (`internal/modules/grammar/*_test.go`, `internal/cli/run_test.go`, `internal/framework/runner/*_test.go`)
 - production glossary module prompt constraints, proposal mapping, validator-chain behavior, confidence-threshold enforcement, diagnostics redaction, repeated-stage behavior, and explicit CLI/runtime integration (`internal/modules/glossary/*_test.go`, `internal/cli/run_test.go`, `internal/framework/runner/*_test.go`)
 - production homophones module prompt constraints, proposal mapping, validator-chain behavior, confidence-threshold enforcement, diagnostics redaction, protected-term behavior, and explicit CLI/runtime integration (`internal/modules/homophones/*_test.go`, `internal/cli/run_test.go`, `internal/framework/runner/*_test.go`)
@@ -493,7 +476,7 @@ Implemented tests currently cover:
 - subprocess operational hardening behavior including large-input, failure-mode, timeout/cancellation, backend-failure, and partial-progress paths (`cmd/audita/main_integration_test.go`)
 - report/diagnostics redaction and artifact-shape behavior across success and failure paths (`internal/cli/run_test.go`, `cmd/audita/main_integration_test.go`)
 
-## Operational hardening status (Phase 18)
+## Operational hardening status
 The runtime now includes hardened subprocess behavior for parent-process callers:
 - deterministic success/failure exit codes;
 - strict stdout/stderr separation suitable for machine orchestration;
@@ -504,9 +487,7 @@ The runtime now includes hardened subprocess behavior for parent-process callers
 
 Operational caller guidance is documented in [`docs/subprocess-operations.md`](docs/subprocess-operations.md).
 
-## Final status (Phase 19 complete)
+## Final status
-- Go Audita is the active implementation.
+- Audita's default full module-sequence runtime is implemented and tested.
-- Default full module-sequence runtime is implemented and tested.
 - Parity fixtures and operational hardening coverage are in place.
-- Python is preserved as a legacy/reference implementation in `python/` and is no longer the primary operational path.
+- Historical migration context is documented in [`docs/migration-from-python.md`](docs/migration-from-python.md).
-- Migration and rollout guidance is documented in [`docs/migration-from-python.md`](docs/migration-from-python.md).

docs/python-parity.md

@@ -1,6 +1,6 @@
 # Python vs Go Parity Notes
 
-This document tracks Phase 17 parity-fixture coverage and differences between the original Python implementation and the Go rewrite.
+This document tracks parity-fixture coverage and intentional differences between historical Python behavior and the current Audita runtime.
 
 ## Scope
 
@@ -54,7 +54,7 @@ Current parity fixtures cover:
 
 ## Open Parity Gaps (Not Intentional)
 
-These are known Phase 17 expansion opportunities and should not be labeled as intentional compatibility differences:
+These are known parity expansion opportunities and should not be labeled as intentional compatibility differences:
 
 1. Broader Python fixture import
 - The current Go parity fixtures are native fixture cases; they do not yet ingest all existing Python test fixtures directly.

docs/rewrite-notes.md

@@ -1,4 +1,7 @@
-# Audita Go Rewrite Notes
+# Audita Rewrite Notes (Historical)
+
+This document is a historical record of the Python-to-Go rewrite project.
+It is retained for engineering context, not as primary runtime guidance.
 
 ## Definition of done for the Go rewrite
 

docs/subprocess-operations.md

@@ -1,4 +1,4 @@
-# Audita Go Subprocess Operations
+# Audita Subprocess Operations
 
 This document describes how parent processes should invoke `audita process` safely in production orchestration.
 

internal/cli/run.go

@@ -542,7 +542,7 @@ func extractErrorPhase(err error) (phase string, message string) {
 
 func buildProcessReport(status string, inv processInvocation, runDir *diagnostics.RunDirectory, startedAt, completedAt time.Time, errorMessage string, errorPhase string, normalizationSummary *normalization.NormalizationSummary, chunkingSummary *chunking.Summary, runOutput *runner.RunOutput) reporting.ProcessReport {
 	report := reporting.ProcessReport{
-		Phase:          "phase16-default-pipeline-integration",
+		Phase:          "default_pipeline",
 		Status:         status,
 		Operation:      "process",
 		TranscriptPath: inv.TranscriptPath,

internal/cli/run_test.go

@@ -750,8 +750,8 @@ func TestRunProcessReportJSONIncludesChunkingSummary(t *testing.T) {
 	if report.Chunking.MaxSectionTokens == 0 {
 		t.Errorf("expected max_section_tokens in report")
 	}
-	if report.Phase != "phase16-default-pipeline-integration" {
+	if report.Phase != "default_pipeline" {
-		t.Errorf("expected phase 'phase16-default-pipeline-integration', got %q", report.Phase)
+		t.Errorf("expected phase 'default_pipeline', got %q", report.Phase)
 	}
 }
 
@@ -1114,7 +1114,7 @@ func TestRunProcessExplicitUnsupportedModulesFailClearly(t *testing.T) {
 }
 
 func TestRunProcessExplicitGrammarAppliesCorrectionAndReportsDiagnostics(t *testing.T) {
-	secret := "phase12-secret"
+	secret := "grammar-secret"
 	processProposalLLMClient = &fakeStructuredLLMClient{
 		proposalResponses: []proposal_generation.StructuredCorrectionSet{
 			{
@@ -1309,7 +1309,7 @@ func TestRunProcessExplicitGrammarMalformedLLMOutputFailsWithErrorLog(t *testing
 }
 
 func TestRunProcessDefaultRunExecutesFullModuleSequence(t *testing.T) {
-	secret := "phase16-secret"
+	secret := "pipeline-secret"
 	proposalClient := &fakeStructuredLLMClient{
 		proposalResponses: []proposal_generation.StructuredCorrectionSet{
 			{Corrections: []proposal_generation.StructuredCorrectionProposal{
@@ -1531,7 +1531,7 @@ func TestRunProcessDefaultFullPipelineFailurePreservesPartialProgressAndRetentio
 }
 
 func TestRunProcessDefaultFullPipelineAggregatesSkipsAndAutoRetentionKeepsRunDir(t *testing.T) {
-	secret := "phase16-retention-secret"
+	secret := "retention-secret"
 	proposalClient := &fakeStructuredLLMClient{
 		proposalResponses: []proposal_generation.StructuredCorrectionSet{
 			{Corrections: []proposal_generation.StructuredCorrectionProposal{
@@ -1648,7 +1648,7 @@ func TestRunProcessDefaultFullPipelineAggregatesSkipsAndAutoRetentionKeepsRunDir
 }
 
 func TestRunProcessExplicitGlossaryAppliesCorrectionAndReportsDiagnostics(t *testing.T) {
-	secret := "phase13-secret"
+	secret := "glossary-secret"
 	proposalClient := &fakeStructuredLLMClient{
 		proposalResponses: []proposal_generation.StructuredCorrectionSet{
 			{
@@ -1923,7 +1923,7 @@ func TestRunProcessExplicitGlossaryMalformedLLMOutputFailsWithErrorLog(t *testin
 }
 
 func TestRunProcessExplicitHomophonesAppliesCorrectionAndReportsDiagnostics(t *testing.T) {
-	secret := "phase14-secret"
+	secret := "homophones-secret"
 	proposalClient := &fakeStructuredLLMClient{
 		proposalResponses: []proposal_generation.StructuredCorrectionSet{
 			{
@@ -2241,7 +2241,7 @@ func TestRunProcessExplicitGlossaryThenHomophonesSeesWorkingTranscriptChanges(t
 }
 
 func TestRunProcessExplicitSpokenWordAppliesCleanupAndReportsDiagnostics(t *testing.T) {
-	secret := "phase15-secret"
+	secret := "spoken-word-secret"
 	proposalClient := &fakeStructuredLLMClient{
 		proposalResponses: []proposal_generation.StructuredCorrectionSet{
 			{

internal/cli/testdata/parity/default-full-pipeline.case.json

@@ -5,8 +5,8 @@
   "proposal_responses_file": "default-full-pipeline.proposals.json",
   "validation_responses_file": "default-full-pipeline.validations.json",
   "env": {
-    "AUDITA_LLM_API_KEY": "phase17-secret",
+    "AUDITA_LLM_API_KEY": "parity-secret",
-    "AUDITA_VALIDATION_LLM_API_KEY": "phase17-secret"
+    "AUDITA_VALIDATION_LLM_API_KEY": "parity-secret"
   },
   "expect": {
     "exit_code": 0,
@@ -16,7 +16,7 @@
     "module_count": 5,
     "total_applied_changes": 3,
     "total_skipped_changes": 3,
-    "secret_markers": ["phase17-secret"],
+    "secret_markers": ["parity-secret"],
     "expected_proposal_calls": [
       "glossary_1:proposal",
       "homophones:proposal",

internal/cli/testdata/parity/default-full-pipeline.validations.json

@@ -7,6 +7,6 @@
   {"validations": [{"correction_index": 0, "approved": true, "confidence": 0.99, "reason": "ok"}]},
   {"validations": [{"correction_index": 0, "approved": true, "confidence": 0.99, "reason": "ok"}]},
   {"validations": [{"correction_index": 0, "approved": false, "confidence": 0.99, "reason": "reject cleanup"}]},
-  {"validations": [{"correction_index": 0, "approved": true, "confidence": 0.99, "reason": "phase17-secret"}]},
+  {"validations": [{"correction_index": 0, "approved": true, "confidence": 0.99, "reason": "parity-secret"}]},
   {"validations": [{"correction_index": 0, "approved": true, "confidence": 0.99, "reason": "ok"}]}
 ]

internal/core/reporting/report_test.go

@@ -11,7 +11,7 @@ import (
 func TestProcessReportModuleResultsJSONSuccessAndSkipped(t *testing.T) {
 	now := time.Now().UTC()
 	report := ProcessReport{
-		Phase:  "phase15-spoken-word-module",
+		Phase:  "default_pipeline",
 		Status: "success",
 		ModuleResults: []ModuleReport{
 			{
@@ -80,7 +80,7 @@ func TestProcessReportModuleResultsJSONSuccessAndSkipped(t *testing.T) {
 func TestProcessReportModuleResultsJSONFailedModule(t *testing.T) {
 	now := time.Now().UTC()
 	report := ProcessReport{
-		Phase:  "phase15-spoken-word-module",
+		Phase:  "default_pipeline",
 		Status: "failed",
 		ModuleResults: []ModuleReport{
 			{

internal/framework/contracts/chunk_proposal_composition_test.go

@@ -13,7 +13,7 @@ import (
 
 // testChunkProposalHarness is a test-only helper that composes existing
 // deterministic chunking and proposal-application primitives.
-// Production runner orchestration is implemented in later phases.
+// It isolates proposal/composition behavior from full runner orchestration.
 type testChunkProposalHarness struct {
 	module TranscriptModule
 }

internal/framework/modules/registry.go

@@ -23,7 +23,6 @@ const (
 
 const (
 	ReasonUnsupportedModule = "unsupported_module"
-	ReasonUnimplementedModule = "unimplemented_module"
 )
 
 var knownModuleKeys = map[string]struct{}{
@@ -66,8 +65,7 @@ type Factory struct {
 	constructors map[string]Constructor
 }
 
-// NewFactory creates a production registry scaffold with known module keys but
+// NewFactory creates a production module registry.
-// no real module constructors registered yet.
 func NewFactory(deps Dependencies) *Factory {
 	factory := &Factory{
 		deps:         deps,
@@ -133,7 +131,7 @@ func (f *Factory) ModuleForSpec(spec contracts.ModuleRunSpec) (contracts.Transcr
 
 	constructor, ok := f.constructors[key]
 	if !ok || constructor == nil {
-		return nil, &UnimplementedModuleError{ModuleKey: key}
+		return nil, fmt.Errorf("internal module registry error: constructor for module %q is not configured", key)
 	}
 
 	module, err := constructor(context.Background(), ConstructRequest{
@@ -170,17 +168,3 @@ func (e *UnsupportedModuleError) Error() string {
 func (e *UnsupportedModuleError) ReasonCode() string {
 	return ReasonUnsupportedModule
 }
-
-// UnimplementedModuleError indicates a known module key without constructor.
-type UnimplementedModuleError struct {
-	ModuleKey string
-}
-
-func (e *UnimplementedModuleError) Error() string {
-	return fmt.Sprintf("module %q is recognized but not implemented", strings.TrimSpace(e.ModuleKey))
-}
-
-// ReasonCode returns a stable reason code suitable for reporting.
-func (e *UnimplementedModuleError) ReasonCode() string {
-	return ReasonUnimplementedModule
-}

internal/framework/modules/registry_test.go

@@ -3,6 +3,7 @@ package modules
 import (
 	"context"
 	"errors"
+	"strings"
 	"testing"
 
 	"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
@@ -64,22 +65,17 @@ func TestUnsupportedUnknownModuleKeyFailsCleanly(t *testing.T) {
 	}
 }
 
-func TestRecognizedButUnimplementedModuleKeyFailsCleanly(t *testing.T) {
+func TestRecognizedButMissingConstructorFailsWithInternalRegistryError(t *testing.T) {
 	factory := NewFactory(Dependencies{})
-	// Force an unimplemented state for a known key to keep reason-code behavior tested.
+	// Force a missing constructor state for a known key.
 	factory.constructors[ModuleKeySpokenWord] = nil
 
 	_, err := factory.ModuleForSpec(contracts.ModuleRunSpec{ModuleKey: ModuleKeySpokenWord, InstanceName: ModuleKeySpokenWord})
 	if err == nil {
-		t.Fatal("expected unimplemented-module error")
+		t.Fatal("expected constructor-missing error")
 	}
-
+	if !strings.Contains(err.Error(), "internal module registry error") {
-	var unimplemented *UnimplementedModuleError
+		t.Fatalf("expected internal registry error, got %v", err)
-	if !errors.As(err, &unimplemented) {
-		t.Fatalf("expected UnimplementedModuleError, got %T (%v)", err, err)
-	}
-	if unimplemented.ReasonCode() != ReasonUnimplementedModule {
-		t.Fatalf("unexpected reason code: %q", unimplemented.ReasonCode())
 	}
 }
 

internal/framework/proposal_generation/generate_test.go

@@ -185,7 +185,7 @@ func TestGenerateCandidatesMultipleSectionsStableMetadata(t *testing.T) {
 }
 
 func TestGenerateCandidatesDiagnosticsWrittenAndRedacted(t *testing.T) {
-	secret := "phase11-secret"
+	secret := "proposal-secret"
 	client := &fakeStructuredClient{
 		responses: []StructuredCorrectionSet{
 			{Corrections: []StructuredCorrectionProposal{{TargetSegmentID: 1, OriginalText: secret, CorrectedText: "safe", Confidence: 0.9}}},

internal/framework/proposals/proposal.go

@@ -30,7 +30,7 @@ type EnrichedCorrectionProposal struct {
 
 // Validate checks only basic structural integrity of the proposal.
 // Semantic checks (staleness, span presence, replacement behavior) are handled
-// by later proposal preview/application and validator phases.
+// by proposal preview/application and validator execution.
 func (p CorrectionProposal) Validate() error {
 	if p.TargetSegmentID <= 0 {
 		return fmt.Errorf("proposal id must be positive")

internal/modules/glossary/module.go

@@ -41,7 +41,7 @@ func New() (*Module, error) {
 func (m *Module) Key() string { return "glossary" }
 
 func (m *Module) ReplacementPolicy() proposals.ReplacementPolicy {
-	// Python glossary module uses replace_all to update repeated term occurrences.
+	// Update repeated term occurrences.
 	return proposals.ReplacementPolicyReplaceAll
 }
 

internal/modules/grammar/module.go

@@ -41,7 +41,7 @@ func New() (*Module, error) {
 func (m *Module) Key() string { return "grammar" }
 
 func (m *Module) ReplacementPolicy() proposals.ReplacementPolicy {
-	// Python grammar module uses require_unique for conservative single-span replacement.
+	// Conservative single-span replacement.
 	return proposals.ReplacementPolicyRequireUnique
 }
 

internal/modules/grammar/prompt.go

@@ -22,8 +22,8 @@ type promptTranscriptSection struct {
 	Segments     []promptSegment `json:"segments"`
 }
 
-// BuildProposalMessages mirrors the Python grammar-module prompt intent:
+// BuildProposalMessages constrains corrections to punctuation/capitalization/
-// punctuation/capitalization/spacing cleanup only, with strict meaning guards.
+// spacing cleanup with strict meaning guards.
 func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary, sectionIndex int) ([]contracts.LLMMessage, error) {
 	glossaryJSON, err := json.MarshalIndent(glossary, "", "  ")
 	if err != nil {

internal/modules/homophones/module.go

@@ -41,7 +41,7 @@ func New() (*Module, error) {
 func (m *Module) Key() string { return "homophones" }
 
 func (m *Module) ReplacementPolicy() proposals.ReplacementPolicy {
-	// Python homophones module uses require_unique for conservative single-span replacement.
+	// Conservative single-span replacement.
 	return proposals.ReplacementPolicyRequireUnique
 }
 

internal/modules/homophones/prompt.go

@@ -22,8 +22,8 @@ type promptTranscriptSection struct {
 	Segments     []promptSegment `json:"segments"`
 }
 
-// BuildProposalMessages mirrors the Python homophones-module prompt intent:
+// BuildProposalMessages constrains corrections to conservative homophone and
-// conservative homophone and mistranscription correction only.
+// mistranscription updates.
 func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary, sectionIndex int) ([]contracts.LLMMessage, error) {
 	glossaryJSON, err := json.MarshalIndent(glossary, "", "  ")
 	if err != nil {

internal/modules/spoken_word/module.go

@@ -41,7 +41,7 @@ func New() (*Module, error) {
 func (m *Module) Key() string { return "spoken_word" }
 
 func (m *Module) ReplacementPolicy() proposals.ReplacementPolicy {
-	// Python spoken_word module uses require_unique for conservative single-span replacement.
+	// Conservative single-span replacement.
 	return proposals.ReplacementPolicyRequireUnique
 }
 

internal/modules/spoken_word/prompt.go

@@ -22,8 +22,8 @@ type promptTranscriptSection struct {
 	Segments     []promptSegment `json:"segments"`
 }
 
-// BuildProposalMessages mirrors the Python spoken_word-module prompt intent:
+// BuildProposalMessages constrains corrections to conservative dysfluency
-// conservative dysfluency cleanup with strict semantic preservation.
+// cleanup with strict semantic preservation.
 func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary, sectionIndex int) ([]contracts.LLMMessage, error) {
 	glossaryJSON, err := json.MarshalIndent(glossary, "", "  ")
 	if err != nil {