utterplan 0.5.1__tar.gz → 0.6.2__tar.gz

{utterplan-0.5.1 → utterplan-0.6.2}/.github/workflows/python-publish.yml

@@ -81,7 +81,8 @@ jobs:
               ]
               assert has_range(requirements, "phrasplit", "0.3.9", "0.4")
               assert has_range(requirements, "ssmd", "0.9.3", "0.10")
-              assert has_range(requirements, "spokenform", "0.4.3", "0.5")
+              assert has_range(requirements, "ttsready", "0.2.3", "0.3")
+              assert has_range(requirements, "renderplan", "0.1.1", "0.2")
               names = set(archive.namelist())
               expected = {
                   "utterplan/py.typed",

{utterplan-0.5.1 → utterplan-0.6.2}/.github/workflows/tests.yml

@@ -49,7 +49,9 @@ jobs:
           python -m pip install \
             "phrasplit==0.3.9" \
             "ssmd==0.9.3" \
-            "spokenform==0.4.3" \
+            "ttsready==0.2.3" \
+            "spokenform==0.4.5" \
+            "renderplan==0.1.1" \
             "typing_extensions==4.0.0" \
             "tomlkit==0.13.0"
           python -m pip install --no-deps -e .
@@ -58,6 +60,26 @@ jobs:
       - name: Run lower-bound tests
         run: python -m pytest -q
 
+  latest-renderplan:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+      - name: Install latest supported dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev]"
+      - name: Run RenderPlan integration tests
+        run: >-
+          python -m pytest -q
+          tests/test_renderplan_batch.py
+          tests/test_renderplan_export.py
+          tests/test_renderplan_replan.py
+          tests/test_cli_render_book.py
+          tests/test_renderplan_dependency_contract.py
   package-smoke:
     runs-on: ubuntu-latest
     steps:
@@ -97,7 +119,8 @@ jobs:
           expected_ranges = {
               "phrasplit": ("0.3.9", "0.4"),
               "ssmd": ("0.9.3", "0.10"),
-              "spokenform": ("0.4.3", "0.5"),
+              "ttsready": ("0.2.3", "0.3"),
+              "renderplan": ("0.1.1", "0.2"),
           }
 
           def check_metadata(contents):
@@ -146,8 +169,11 @@ jobs:
             "$RUNNER_TEMP"/dist/utterplan-*.whl
       - name: Run installed smoke checks
         run: |
+          cd "$RUNNER_TEMP"
           "$RUNNER_TEMP/utterplan-wheel-venv/bin/python" -c \
             "import importlib.metadata as m; import utterplan; assert m.version('utterplan') == utterplan.__version__"
+          "$RUNNER_TEMP/utterplan-wheel-venv/bin/python" -c \
+            "import utterplan.renderplan_batch; from renderplan import RenderPlanSet"
           "$RUNNER_TEMP/utterplan-wheel-venv/bin/utterplan" --version
           cat > "$RUNNER_TEMP/test.ssmd.md" <<'EOF'
           ---
@@ -163,6 +189,61 @@ jobs:
             > "$RUNNER_TEMP/test.utterplan.toml"
           "$RUNNER_TEMP/utterplan-wheel-venv/bin/utterplan" validate \
             "$RUNNER_TEMP/test.utterplan.toml"
+          BOOK="$RUNNER_TEMP/render-book.smoke.ssmdbook"
+          mkdir -p "$BOOK/chapters" "$BOOK/utterplan"
+          cat > "$BOOK/chapters/chapter-0001.ssmd.md" <<'EOF'
+          ---
+          ssmd_version: "0.9"
+          language: en-US
+          ---
+          Installed wheel render-book smoke.
+          EOF
+          cat > "$BOOK/manifest.json" <<'EOF'
+          {
+            "format": "ssmdconvert.book",
+            "schema_version": 1,
+            "ssmd_version": "0.9",
+            "chapters": [
+              {
+                "id": "chapter-0001",
+                "source_number": 1,
+                "path": "chapters/chapter-0001.ssmd.md",
+                "title": "Chapter 1"
+              }
+            ]
+          }
+          EOF
+          "$RUNNER_TEMP/utterplan-wheel-venv/bin/utterplan" compile \
+            "$BOOK/chapters/chapter-0001.ssmd.md" --lang en-us --text-preparation identity \
+            -o "$BOOK/utterplan/chapter-0001.utterplan.toml"
+          "$RUNNER_TEMP/utterplan-wheel-venv/bin/python" - "$BOOK/narration.renderprofile.toml" <<'PY'
+          import sys
+          from pathlib import Path
+
+          from renderplan import PausePolicy, PlanningPolicy, RenderProfile, RoleProfile
+          from renderplan import codec
+
+          profile = RenderProfile(
+              roles={"narrator": RoleProfile(language="en-US", binding={"engine": "smoke"})},
+              default_role="narrator",
+              planning=PlanningPolicy(split="sentence"),
+              pauses=PausePolicy(mode="manual"),
+          )
+          codec.save_profile(profile, Path(sys.argv[1]))
+          PY
+          "$RUNNER_TEMP/utterplan-wheel-venv/bin/utterplan" render-book \
+            "$BOOK" --profile "$BOOK/narration.renderprofile.toml" --chapters 1
+          "$RUNNER_TEMP/utterplan-wheel-venv/bin/python" - "$BOOK" <<'PY'
+          import sys
+          from pathlib import Path
+
+          from renderplan import load_renderplan_set
+
+          book = Path(sys.argv[1])
+          set_path = next((book / "renderplan").glob("*/renderplan-set.toml"))
+          renderplan_set = load_renderplan_set(set_path)
+          assert [chapter.id for chapter in renderplan_set.chapters] == ["chapter-0001"]
+          PY
           cat > "$RUNNER_TEMP/test-0.8.ssmd.md" <<'EOF'
           ---
           ssmd_version: "0.8"
@@ -177,8 +258,13 @@ jobs:
             exit 1
           fi
           grep -q "header.version_unsupported" "$RUNNER_TEMP/test-0.8.out"
-          "$RUNNER_TEMP/utterplan-wheel-venv/bin/utterplan" migrate \
-            "$GITHUB_WORKSPACE/tests/schema_history/v1/basic.json" --check
+          if "$RUNNER_TEMP/utterplan-wheel-venv/bin/utterplan" migrate \
+            "$GITHUB_WORKSPACE/tests/schema_history/v1/basic.json" --check > "$RUNNER_TEMP/migration-check.out" 2>&1; then
+            cat "$RUNNER_TEMP/migration-check.out"
+            echo "Expected historical schema migration to require recompilation" >&2
+            exit 1
+          fi
+          grep -q "migration.recompile_required" "$RUNNER_TEMP/migration-check.out"
           "$RUNNER_TEMP/utterplan-wheel-venv/bin/utterplan" inspect \
             "$RUNNER_TEMP/test.utterplan.toml" --segment 0
 

utterplan-0.6.2/AGENTS.md

@@ -0,0 +1,29 @@
+# AGENTS.md
+
+<!-- Generated by memoryledger. Do not edit directly. -->
+<!-- Source: memoryledger records; regenerate with `memoryledger render` and `memoryledger export`. -->
+
+## Project memory policy
+
+This file contains reviewed long-term project memory.
+
+## Rules
+
+- UtterPlan is engine-independent. Core code must not import PyKokoro, PiperSynth, kokorog2p, piperg2p, ONNX Runtime, audio packages, or any consumer package.
+- UtterPlan ends before G2P. Engine/model selection, synthesis, and audio composition happen downstream.
+- `.utterplan.toml` schema v7 is the current inter-package contract; schema-v5/v6 TOML and historical JSON schemas v1–v4 remain sequential migration inputs only, and only the current schema version is natively supported.
+- Python objects may not contain semantic state that cannot survive file roundtrip.
+- Public FlowPlan objects contain no phonemes, model token IDs, models, sessions, or audio; completed plans must not retain spaCy or provider documents.
+- Every offset has a documented coordinate space.
+- Default planning is deterministic; the same source and configuration always produce the same executable plan and `plan_id`.
+- Schema changes require explicit compatibility review, frozen historical fixture coverage, deterministic migration tests, and package artifact checks.
+- Released schema files are immutable and retained under versioned paths; schemas v5, v6, and v7 have no JSON Schema resources.
+- Every supported older schema must retain a sequential migration path to current (v1 through v6 feed v7).
+- Migrations operate on serialized plain data and may not call parser, planner, G2P, renderer, or audio stages.
+- Package version and schema version remain independent. Migration preserves a compiled plan; replanning is a separate operation.
+- Optional compiler traces are sidecars; they must never alter executable plan content or identity.
+- UtterPlan parses SSMD 0.9 only; it does not parse SSMD 0.8 or migrate source documents (`ssmd migrate` owns that).
+- Book commands (`compile-book`, `render-book`) read the SSMDBook manifest only for chapter discovery, never modify the manifest or source chapters, write derived plans to separate directories, and never build book-level combined plans.
+- RenderPlan projection is optional: VoiceRender creates and validates engine-backed RenderProfiles, while UtterPlan projects stored schema-v7 FlowPlans into profile-specific RenderPlans (with `renderplan-set.toml` and reports) and performs deterministic replan refinement only.
+- UtterPlan depends directly on SSMD, PhraseSplit, TTSReady, and the renderplan contract package only; production code does not import Spokenform, and spaCy stays optional best-effort enrichment.
+- Repository tests must be self-contained and must not require sibling consumer checkouts; consumer-specific compatibility testing belongs in the consumer repository.

{utterplan-0.5.1 → utterplan-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: utterplan
-Version: 0.5.1
+Version: 0.6.2
 Summary: Engine-independent text-to-speech planning compiler and interchange format
 Author-email: Holger Nahrstaedt <nahrstaedt@gmail.com>
 License:                                  Apache License
@@ -224,9 +224,10 @@ License-File: LICENSE
 License-File: NOTICE
 Requires-Dist: phrasplit<0.4,>=0.3.9
 Requires-Dist: ssmd<0.10,>=0.9.3
-Requires-Dist: spokenform<0.5,>=0.4.3
+Requires-Dist: ttsready<0.3,>=0.2.3
 Requires-Dist: typing_extensions>=4.0
 Requires-Dist: tomlkit<1,>=0.13
+Requires-Dist: renderplan<0.2,>=0.1.1
 Provides-Extra: dev
 Requires-Dist: build; extra == "dev"
 Requires-Dist: jsonschema; extra == "dev"
@@ -250,9 +251,9 @@ Dynamic: license-file
 
 UtterPlan is the canonical, engine-independent semantic compiler from one SSMD
 document (or explicitly selected plain-text document) to an executable speech
-plan. It produces deterministic prepared text, ordered flow units, segment-local
-semantics, pause intents, portable document metadata, and typed directives for
-independent consumers such as ttsready and Readio. It does not manage or modify book workspaces; `compile-book` reads an SSMDBook manifest only to discover selected source chapters. It stops before G2P, synthesis, and audio.
+plan. It produces deterministic prepared text, paragraph-local flow units, safe boundary opportunities, authored pause intents, and segment-local
+semantics, portable document metadata, and typed directives for
+independent downstream consumers such as Readio, VoiceRender, and other FlowPlan users. Its book commands read the SSMDBook manifest only for chapter discovery, never modify the manifest or source chapters, and write derived plans to separate directories. It uses TTSReady for written-to-spoken preparation and stops before G2P, synthesis, and audio.
 
 ## CLI
 
@@ -282,7 +283,7 @@ Compile independent documents incrementally; every successful plan is saved imme
 utterplan compile-many examples/*.ssmd --output-dir build/plans
 ```
 
-This writes one `.utterplan.toml` per source plus an atomically refreshed `compile-report.toml`. Use `--fail-fast` to skip later inputs after a failure, `--force` to replace existing plans, or `--report PATH` to choose another report location.
+This writes one `.utterplan.toml` per source plus an atomically refreshed `compile-report.toml`. Terminal diagnostics default to warnings; `--diagnostics all` also prints informational records, while `--diagnostics none` suppresses non-failure details. Failures are always reported, and the operational report retains every diagnostic. Use `--fail-fast` to skip later inputs after a failure, `--force` to replace existing plans, or `--report PATH` to choose another report location.
 
 Compile a selected chapter range directly from an editable SSMDBook workspace:
 
@@ -292,7 +293,7 @@ cd "Platform Decay - Martha Wells.ssmdbook"
 utterplan compile-book chapters --chapters 5-17
 ```
 
-The command reads the workspace manifest to discover chapters and writes independent v5 plans and a report under `utterplan/`:
+The command reads the workspace manifest to discover chapters and writes independent v7 plans and a report under `utterplan/`:
 
 ```text
 utterplan/
@@ -303,7 +304,59 @@ utterplan/
 └── chapter-0017.utterplan.toml
 ```
 
-Omit `--chapters` to compile all manifest chapters. Use comma-separated source-number selections for non-contiguous ranges, for example `utterplan compile-book chapters --chapters 1,3-5`. The book root itself is also accepted as input; see the [SSMDBook guide](docs/ssmdbook.md).
+Omit `--chapters` to compile all manifest chapters. Use comma-separated source-number selections for non-contiguous ranges, for example `utterplan compile-book chapters --chapters 1,3-5`. `--diagnostics warnings|all|none` defaults to warnings; failures are always shown and reports retain complete diagnostics. The book root itself is also accepted as input; see the [SSMDBook guide](docs/ssmdbook.md).
+
+## From an SSMDBook to RenderPlans
+
+UtterPlan keeps one canonical semantic plan per chapter. A RenderProfile is a
+separate renderer configuration; create and validate it with VoiceRender, then
+project the selected saved plans into a profile-specific RenderPlan collection:
+
+```bash
+voicerender profile create \
+  --engine piper \
+  --target en_US-amy-medium \
+  --language en-US \
+  --offline \
+  --output narration.renderprofile.toml
+voicerender profile validate narration.renderprofile.toml
+
+utterplan compile-book . --chapters 5-17
+utterplan render-book . --chapters 5-17 --profile narration.renderprofile.toml
+```
+
+The book's `utterplan/` directory remains the shared semantic source. The new
+command writes independent renderer-specific plans into a deterministic variant:
+
+```text
+renderplan/
+└── narration--<profile-fingerprint>/
+    ├── renderprofile.toml
+    ├── renderplan-set.toml
+    ├── render-report.toml
+    ├── chapter-0005.renderplan.toml
+    └── ...
+```
+
+The variant label comes from the profile filename by default; its suffix is the
+first 12 hexadecimal characters of the canonical RenderProfile `profile_id`.
+Changing identity-bearing profile semantics selects a different directory, so
+multiple voices or planning policies can coexist without replacing one another.
+Each variant snapshots the canonical profile; `renderplan-set.toml` records its
+full identity, source profile reference, and chapter plan IDs. `--variant` changes
+the human label without removing the fingerprint, and `--output-root` changes the
+collection root while retaining the automatic variant directory.
+
+`render-book` consumes only the existing schema-v7 UtterPlans and shared
+RenderProfile/RenderPlan contract. VoiceRender is not required to run it: VoiceRender
+creates or refreshes engine-backed profiles, then preflights and renders the
+resulting RenderPlans. The single-file `utterplan render-plan` command remains the
+low-level projection and deterministic replan primitive.
+
+Related packages: [RenderPlan](https://pypi.org/project/renderplan/) defines the
+shared profile and plan contracts; [VoiceRender](https://pypi.org/project/voicerender/)
+creates engine-backed profiles and performs preflight and synthesis.
+
 The CLI also provides:
 
 ```bash
@@ -314,10 +367,14 @@ utterplan inspect chapter.utterplan.toml --boundaries --tokens
 utterplan explain chapter.utterplan.toml --trace chapter.trace.toml
 utterplan inspect-trace chapter.trace.toml --preparation --boundaries
 utterplan inspect-attempt chapter.attempt.toml --issues
+utterplan preview chapter.utterplan.toml --segments 58-62 --chunk-by clause --pause-policy automatic
+utterplan render-plan chapter.utterplan.toml --profile voice.renderprofile.toml -o chapter.renderplan.toml --explain
 ```
 
 `explain` presents executable flow as a human-readable speech plan. Use `compile --trace PATH` to retain optional compiler provenance; `explain --trace PATH` and `inspect-trace` read that sidecar separately from the plan.
 
+`render-plan` projects only current schema-v7 FlowPlans into the shared RenderPlan contract. Replanning requires both the exact previous RenderPlan and its matching preflight report; UtterPlan refines only failed speech occurrences and does not calculate renderer-specific metrics.
+
 `inspect-attempt` reads the separate `utterplan.planning-attempt.v1` TOML artifact,
 not a canonical plan. Use it to review renderability issues and safe repair
 assessments on blocked planning outcomes; such candidates remain inspect-only drafts.
@@ -337,18 +394,18 @@ command:
 ssmd migrate old.ssmd --to 0.9
 ```
 
-`utterplan migrate` explicitly imports supported historical `.utterplan.json` plans and writes current TOML. It does not migrate SSMD source.
+`utterplan migrate` handles only serialized plan data; v6-to-v7 migration refuses with `migration.recompile_required` when the saved plan cannot prove complete boundary coverage. Recompile the original source to produce a current plan. It does not migrate SSMD source.
 Normal plan loading is TOML-only: `FlowPlan.load()` and plan-inspection commands reject JSON rather than auto-detecting it.
 
 ## Planning defaults
 
-The minimal CLI defaults are explicit: `spokenform` is the default text-preparation backend, `tts` is the default pause activation mode, and `spacy off` is the default linguistic-resource policy. With `spacy off`, UtterPlan uses its deterministic fallback tokenizer and analysis and does not depend on an installed spaCy model.
+The CLI and Python planner default to best-effort spaCy enrichment (`auto`). UtterPlan prefers an already-installed compatible model in `sm`, `md`, `lg`, `trf` order; if spaCy or every compatible local model is unavailable, planning continues with deterministic fallback tokens. UtterPlan never downloads models. Use `--spacy off` or `LinguisticsConfig(use_spacy=False)` to opt out, or request an explicit tier to require that local model.
 
 Python `PlannerConfig` defaults to `document_format="plain"`; set it to `"ssmd"` when a Python string contains SSMD source.
 
 Python `PlannerConfig.renderability_mode` also defaults to safe punctuation-only repair; choose `"strict"` to reject every repair opportunity. Neither mode guesses a symbol's pronunciation or crosses semantic blockers.
 
-`spacy auto` is opt-in. When enabled and a compatible local model is available, UtterPlan may expose richer tokenization, POS tags, lemmas, and tags; `auto` is not the default.
+V7 `token.span`, `pos`, `tag`, `lemma`, and `morph` describe the prepared `segment.text` and are the downstream linguistic context, not engine/model token counts; consumers should not retokenize or rerun spaCy. Optional `replacement.span` / `replacement.source` records compact preparation provenance (for example, `A R T` from `ART`): spans index final prepared segment text, while full source coordinates and maps remain in the optional trace sidecar. Replacement provenance does not change executable hashes or synthesis inputs.
 
 ## Python API
 
@@ -380,6 +437,20 @@ identity. Plain text must be explicitly selected in Python and always requires a
 language fallback. Existing `UtterancePlanner.plan` remains supported and returns
 only the plan; TOML is the portable persistence and interchange format.
 
+The optional RenderPlan producer consumes the stored prepared plan directly:
+
+```python
+from renderplan.codec import load_profile, save_plan
+from utterplan import FlowPlan, build_render_plan
+
+source = FlowPlan.load("chapter.utterplan.toml")
+profile = load_profile("voice.renderprofile.toml")
+render_plan = build_render_plan(source, profile)
+save_plan(render_plan, "chapter.renderplan.toml")
+```
+
+Use `build_render_plan(..., previous_plan=previous, preflight=report)` for deterministic refinement; both values are required together. The RenderPlan path rejects historical UtterPlan schemas and does not depend on a renderer or audio runtime. See the [RenderPlan CLI](docs/cli.md#produce-or-replan-a-renderplan) and [Python API](docs/python-api.md#build-and-replan-a-renderplan) guides.
+
 For operational progress from a long-running Python plan, pass `on_progress` to
 `UtterancePlanner.plan`, `UtterancePlanner.compile`, or `compile_document`. The
 callback receives typed `PlannerProgressEvent` objects and does not change the plan:
@@ -398,7 +469,16 @@ Callbacks run synchronously and exceptions propagate. See the [Python API guide]
 
 ## Renderer-consumer boundary
 
-Renderers consume `FlowPlan.flow` in order. Each `FlowUnit` contains local `FlowSegment` objects with already-prepared speech text, effective language, segment-local token views, semantic pause intents, directives, markers, and optional heading level. Token `start`/`end` offsets are Python-character indexes into that segment's `text`; they are never document-global coordinates. Pause intents express `none`, semantic strengths, or exact authored times and do not prescribe engine-specific duration policy.
+Renderers consume `FlowPlan.flow` in order. Each `FlowUnit` contains local `FlowSegment` objects with already-prepared speech text, effective language, segment-local linguistic token views, canonical boundary opportunities, authored pause intents, directives, markers, and optional heading level. Token `start`/`end` offsets are Python-character indexes into that segment's `text`; they are never document-global coordinates. FlowUnits are fixed paragraph-local blocks, not renderer chunks; a `FlowSegment` is not necessarily one TTS call. `boundary_before` / `boundary_after` hold safe cut opportunities independently from authored `none`, strength, or timed pause intents. Consumers may choose sentence, paragraph, or engine-token-budget chunking and native, automatic, or manual pause realization; linguistic token views are not model-token counts.
+
+For renderer-neutral chunk tests and debugging, `preview_plan()` projects stored text and boundaries without changing the plan:
+
+```python
+from utterplan import FlowPlan, preview_plan
+
+plan = FlowPlan.load("chapter.utterplan.toml")
+chunks = preview_plan(plan, chunk_by="clause", pause_policy="automatic")
+```
 
 `FlowPlan.document` carries compact document metadata and `FlowPlan.linguistics` identifies the analysis provider without retaining provider documents. Compiler source, preparation maps, diagnostics, and renderability details belong only in an optional trace sidecar. Plans contain no phonemes, model token IDs, models, sessions, renderer configuration, provider documents, or audio. UtterPlan does not fetch media or execute extension handlers.
 The intended dependency direction is:
@@ -427,9 +507,9 @@ renderer repository rather than UtterPlan's test suite.
 
 ## Versions
 
-The package version is dynamically derived from Git tags by setuptools-scm. Package version and UtterPlan schema version are independent. Current `.utterplan.toml` plans use semantic schema v5. Historical JSON Schemas v1–v4 remain immutable and supported through sequential migrations; v5 deliberately has no JSON Schema resource because its canonical executable contract is the validated TOML/FlowPlan model.
+The package version is dynamically derived from Git tags by setuptools-scm. Package version and UtterPlan schema version are independent. Current `.utterplan.toml` plans use semantic schema v7. Historical JSON Schemas v1–v4 remain immutable; schemas v5, v6, and v7 use versioned TOML/FlowPlan contracts and have no JSON Schema resources.
 
-Schema v5 is a breaking redesign around ordered flow units and segment-local semantics. It preserves deterministic output and moves preparation/source provenance to an optional TOML trace sidecar, which does not affect plan identity. Migration converts serialized plan data only: v1–v4 migrate sequentially to v5 without reparsing, NLP, planning, G2P, rendering, or audio processing. The v4-to-v5 projection fails safely when historical token coordinates or pause semantics cannot be verified.
+Schema v5 introduced ordered flow units and segment-local semantics; v6 added optional exact-source provenance. Schema v7 removes renderer-selected root `unit` and adds canonical safe-boundary opportunities separate from authored pause intents; boundaries participate in v7 executable identity. Older schemas retain sequential data-only migration steps through v6, but v6-to-v7 returns `migration.recompile_required` because the complete boundary inventory cannot be reconstructed. Migrations never reparse, run NLP, plan, call G2P, render, or process audio.
 
 ## Development