Complete Phase 3 proposal foundation

README.md

@@ -2,28 +2,33 @@
 
 Audita is a transcript polishing CLI. The Go implementation at the repository root is canonical going forward, and is being delivered compatibility-first against the frozen Python reference in `python/`.
 
-## Current Status: Phase 2 Foundation
+## Current Status: Phase 3 Deterministic Foundation
 
-The current `audita process` implementation now includes deterministic input handling and normalization foundations:
+The current `audita process` implementation includes deterministic input handling and foundation behavior:
 
 - typed transcript parsing for both accepted top-level forms (`[]` and `{ "segments": [...] }`);
 - typed glossary YAML parsing;
 - transcript and glossary schema validation with actionable errors;
 - deterministic same-speaker normalization;
 - sequential normalized segment IDs starting at `1`;
+- deterministic token estimation;
+- contiguous transcript chunking and section summaries;
 - normalized transcript JSON output;
-- minimal structured `--report-json` output including normalization summary fields;
+- minimal structured `--report-json` output including normalization and chunking summary fields;
 - minimal normalization diagnostics artifacts in per-run work directories;
+- chunking diagnostics artifacts in per-run work directories;
 - subprocess-safe stdout/stderr behavior.
 
-Still not implemented in Phase 2:
+The repository also now contains deterministic proposal foundation packages (models, preview, application, skip reporting, and framework contracts) with fixture/golden tests.
 
-- transcript-polishing correction modules;
+Still not implemented in the Go CLI runtime path:
-- chunking/proposal generation and application;
+
-- deterministic and LLM validators;
+- real module execution pipeline;
-- structured LLM client execution;
+- real `glossary`, `homophones`, `spoken_word`, or `grammar` module behavior;
-- module pipeline execution;
+- LLM proposal generation;
-- full long-term diagnostics retention/reporting model.
+- validator-chain execution;
+- concrete structured LLM client implementation;
+- final end-to-end transcript polishing behavior.
 
 ## Quick Start (Go)
 
@@ -40,13 +45,13 @@ go run ./cmd/audita --help
 go run ./cmd/audita process --help
 ```
 
-Run Phase 2 normalization flow:
+Run current deterministic flow:
 
 ```sh
 go run ./cmd/audita process transcript.json --glossary glossary.yaml --output corrected.json
 ```
 
-Without `--output`, normalized transcript JSON is written to stdout.
+Without `--output`, transcript JSON is written to stdout.
 
 ## Repository Notes
 

docs/rewrite-notes.md

@@ -591,64 +591,11 @@ Before accepting a phase implementation, check:
 - Does `go test ./...` pass?
 - Is the code idiomatic Go rather than Python-shaped Go?
 
-## Phase 2 Status (Go Implementation)
+## Historical checkpoint note
 
-The Go rewrite has completed Phase 2 with the following capabilities:
+Earlier "Phase 2 status" notes are intentionally superseded by
-
+`Current Go rewrite status (Phase 3 foundation)` near the top of this document.
-### Implemented Features:
+Use that section as the authoritative current-state snapshot.
-
-1. **Typed Schema Validation**:
-   - Transcript validation supports both bare segment arrays and objects with `segments` field
-   - Glossary validation matches the existing YAML format
-   - Comprehensive field validation and error reporting
-
-2. **Deterministic Normalization**:
-   - Chronological sorting of segments
-   - Same-speaker adjacent segment merging with configurable gap thresholds
-   - Ellipsis insertion for gaps above the ellipsis threshold
-   - Configurable maximum segment duration and token limits
-   - Sequential ID reassignment starting at 1
-   - Category preservation during merging
-
-3. **Process Output**:
-   - Output is normalized transcript JSON (not raw passthrough)
-   - Canonical transcript shape as specified in architecture docs
-   - Proper stdout/stderr discipline preserved from Phase 1
-
-4. **Enhanced Reporting**:
-   - Success reports include normalization statistics
-   - Failure reports include error phase and concise messages
-   - No secrets leaked to reports
-
-5. **Minimal Diagnostics**:
-   - Per-run work directories with unique timestamps
-   - Source transcript artifacts (raw and parsed)
-   - Normalized transcript artifacts
-   - Normalization summary artifacts
-   - Authoritative report.json in run directory
-   - Error logs on failure
-   - Basic retention policy implementation
-
-### Not Yet Implemented (Future Phases):
-
-- Chunking and token-bounded section building
-- LLM proposal generation and structured output
-- Validator chains and decision logging
-- Module execution pipeline
-- Full diagnostics retention policy
-- Skipped correction detection for auto retention
-- Real module implementations (glossary, homophones, spoken_word, grammar)
-
-### Compatibility Notes:
-
-The Go implementation maintains the public CLI contract from the Python implementation:
-- `audita process transcript.json --glossary glossary.yaml --output corrected.json`
-- stdout contains transcript JSON when --output is omitted
-- stderr contains logs and errors only
-- --report-json writes machine-readable reports
-- Nonzero exit codes on failure
-
-The normalization behavior is deterministic and matches the architectural specifications, but may differ from Python-era behavior in edge cases until full module implementation is complete.
 
 ## When to consider an HTTP API
 

internal/cli/run.go

@@ -494,7 +494,7 @@ func hasHelpFlag(args []string) bool {
 }
 
 func writeRootUsage(w io.Writer) {
-	fmt.Fprintln(w, "Audita is a transcript polishing CLI.")
+	fmt.Fprintln(w, "Audita is a transcript processing CLI.")
 	fmt.Fprintln(w)
 	fmt.Fprintln(w, "Usage:")
 	fmt.Fprintln(w, "  audita <command> [options]")