@interf/compiler 0.4.0 → 0.5.0

package/README.md

@@ -2,25 +2,22 @@
 
 Prepare local datasets for accurate agent use.
 
-Interf Compiler runs a local data-processing workflow over your dataset to build a compiled workspace: a file-based layer on top of your raw files that gives agents the full picture of the dataset they need to answer questions accurately.
+Interf Compiler runs a local data-processing workflow over your dataset to build a file-based layer on top of your raw files that gives agents the full picture they need to answer questions accurately.
 
-Define truth checks to measure how accurately agents answer from your dataset.
+Define truth checks for your dataset, measure a baseline on the raw files, then compile and retest the compiled dataset on the same checks.
 
-Start with a baseline on your files as-is.
-
-Then compile the workspace and retest it on the same checks so you can measure whether it actually helps.
-
-Then run self-improving loops that revise the workflow, rebuild the workspace, and rerun the same truth checks until the workspace passes or reaches the loop limit.
+If it still fails, self-improving loops can revise the workflow, rebuild the compiled dataset, and rerun the same checks until it passes or reaches the loop limit.
 
 ## Why Use It
 
 Interf Compiler is built around a few simple principles:
 
-- `Local`: the dataset, workflow, workspace, and test runs stay on your machine.
-- `File-based`: the compiled workspace is normal folders and files you can inspect, review, and version.
-- `Source-backed`: your raw files stay the source of truth; the compiled workspace is a layer on top, not a replacement database.
-- `Interoperable`: the same workspace can be used with different local agents and tools.
-- `Self-improving`: when truth checks fail, Interf can retry the workflow or revise it, rebuild the workspace, and rerun the same checks.
+- `Explicit`: the compiled dataset is a real folder you can inspect, review, and version.
+- `Yours`: the dataset, workflow, compiled dataset, and test runs stay on your machine and in your control.
+- `File over app`: the compiled dataset is normal files and folders, not hidden app state.
+- `Source-backed`: your raw files stay the source of truth; the compiled dataset is a layer on top, not a replacement database.
+- `Bring your own agent`: the same compiled dataset can be used with different local agents and tools.
+- `Self-improving`: when truth checks fail, Interf can retry the workflow or revise it, rebuild the compiled dataset, and rerun the same checks.
 
 ## Example: Truth Checks
 
@@ -31,9 +28,10 @@ A maintained public test run in this repo uses checks like this:
 <!-- PUBLIC_TEST_CHECKS:START -->
 ```jsonc
 {
-  "workspaces": [
+  "datasets": [
     {
       "name": "cbre-chart-sanity",
+      "path": ".",
       "about": "Bristol historical take-up and availability chart lookup.",
       "checks": [
         {
@@ -53,21 +51,21 @@ A maintained public test run in this repo uses checks like this:
 
 ## Example: `interf test`
 
-`interf test` compares the raw files and the compiled workspace on the same saved truth checks.
-The table below is synced from a real public test run in this repo.
+`interf test` compares files as-is and the compiled dataset on the same saved truth checks.
+That is the point of `interf test`: measure the same checks on both sides and keep the result honest on your own dataset, instead of relying on a frozen benchmark snapshot in the docs.
 
-<!-- PUBLIC_TEST_TABLE:START -->
-| Runner | Files as-is | Compiled workspace |
+A recent maintained internal run on the CBRE chart sanity dataset produced:
+
+<!-- PUBLIC_BENCHMARK_TABLE:START -->
+| Agent | Files as-is | Compiled dataset |
 | --- | --- | --- |
 | Codex (GPT-5.4, xhigh) | `2/2` | `2/2` |
-| Claude Code (Claude Opus 4.6 1M, max) | `0/2` | `2/2` |
-<!-- PUBLIC_TEST_TABLE:END -->
-
-That is the point of `interf test`: measure the same checks on both sides and keep the result honest, even when a compiled workspace helps one model more than another.
+| Claude Code (Claude Opus 4.6, max) | `0/2` | `2/2` |
+<!-- PUBLIC_BENCHMARK_TABLE:END -->
 
-Use `interf test` on your own dataset to measure files as-is versus the compiled workspace on the same checks.
+Use `interf test` on your own dataset to measure files as-is versus the compiled dataset on the same checks.
 
-Each run saves one comparison record under `.interf/tests/runs/`. Detailed target-specific runs and preserved sandboxes stay under `.interf/tests/targets/`.
+Each dataset keeps one latest comparison under `interf/<dataset>/tests/latest.json`. Target-specific runs stay under `interf/<dataset>/tests/file-as-is/runs/` and `interf/<dataset>/tests/compiled/runs/`.
 
 ## Quick Start
 
@@ -82,47 +80,48 @@ Install:
 npm install -g @interf/compiler
 ```
 
-Start from the folder that already contains your dataset:
+Start from a project folder that contains one or more dataset folders:
 
 ```bash
-cd ~/my-dataset
+cd ~/my-interf-project
 interf
+interf test
 interf compile
 interf test
 ```
 
 The first run can:
 
-- save a few truth checks for the dataset
+- draft `interf.json`
+- auto-create a draft set of truth checks for a dataset folder, or let you add them manually
 - test your files as-is first on those same checks
-- build the compiled workspace
-- test the compiled workspace on the same truth checks
+- build the compiled dataset
+- test the compiled dataset on the same truth checks
 
 ## What Interf Compiler Creates
 
-After setup, the main persistent object is the compiled workspace:
-
-- `interf/workspaces/<name>/` with the compiled workspace
-- `interf/workspaces/<name>/.interf/interf.json` with the workspace-local runtime contract
-- `interf/workspaces/<name>/.interf/tests/runs/...` with saved raw-vs-compiled test comparisons
+After setup, the project root stays simple:
 
-The dataset root can also keep `interf.config.json` as bootstrap/setup for workspace names, truth checks, and compile defaults.
+- `interf.json` at the root holds your saved dataset entries and truth checks
+- `interf/` is created only when Interf has artifacts to save
+- `interf/<dataset>/compiled/` is the compiled dataset
+- `interf/<dataset>/tests/` is the saved comparison history for that dataset
 
-A compiled workspace is a folder on top of your dataset. It includes:
+A compiled dataset is a folder on top of your dataset. It includes:
 
-- a workspace-local `raw/` snapshot for direct evidence and verification
+- a local `raw/` snapshot for direct evidence and verification
 - agent-readable summaries and cross-file notes
 - `AGENTS.md`, `CLAUDE.md`, and generated local query skills
-- workspace method, test, and runtime state under `.interf/`
+- workflow, test, and runtime state under `.interf/`
 
-The compiled workspace is the folder your agent should work from.
+The compiled dataset is the folder your agent should work from.
 
 ## How It Works
 
-1. Save a few truth checks for the dataset.
-2. Optionally test your files as-is for a baseline.
-3. Build the compiled workspace.
-4. Test the compiled workspace on the same truth checks.
+1. Save a few truth checks for a dataset in `interf.json`.
+2. Optionally test the files as-is for a baseline.
+3. Build the compiled dataset for that dataset.
+4. Test the compiled dataset on the same truth checks.
 5. Optionally let Interf retry or improve the workflow until it passes or hits the configured limit.
 
 Truth checks are simple:
@@ -136,7 +135,7 @@ Good first truth checks are small and practical:
 - one short statement that should be true or false
 - one simple comparison across years, files, or sections
 
-If `interf.config.json` is missing, `interf` or `interf init` can draft it with you before the first compile. If the compiler cannot find your local agent or compile setup, run:
+If `interf.json` is missing, `interf` or `interf init` can draft it with you before the first compile. If the compiler cannot find your local agent or compile setup, run:
 
 ```bash
 interf doctor
@@ -144,38 +143,41 @@ interf doctor
 
 ## What `interf test` Does
 
-By default, if a compiled workspace exists, it runs both sides and saves one comparison under that workspace's `.interf/tests/runs/`.
+By default, if a compiled dataset exists, it runs both sides and saves one latest comparison under `interf/<dataset>/tests/latest.json`.
+
+You can also select one or more detected local agents in the CLI and compare them in one table.
 
 For live runs:
 
-- raw tests execute from a sanitized raw-only shell built from `raw/`
-- compiled-workspace tests execute from a copied workspace sandbox with embedded sanitized `raw/`
-- both sides use the same saved truth checks from that workspace's `.interf/interf.json`
-- neither sandbox includes the dataset control plane
-- detailed raw/workspace target runs are kept under `.interf/tests/targets/runs/`
-- failed test sandboxes are kept automatically under `.interf/tests/targets/sandboxes/`
+- files-as-is tests execute from a sanitized raw-only shell built from the selected dataset folder
+- compiled-dataset tests execute from a copied compiled sandbox with embedded sanitized `raw/`
+- both sides use the same saved truth checks from `interf.json`
+- neither sandbox includes the project control plane
+- detailed dataset-visible runs are kept under `interf/<dataset>/tests/file-as-is/runs/` and `interf/<dataset>/tests/compiled/runs/`
+- local detailed target runs and preserved sandboxes stay under `.interf/tests/targets/`
+- failed test sandboxes are kept automatically
 - `interf test --keep-sandboxes` keeps every sandbox, even successful ones
 
-From inside a workspace, `interf test` uses that workspace's `.interf/interf.json` directly. From the dataset root, `interf.config.json` only bootstraps workspace selection before the workspace-local runtime contract takes over.
+From inside a compiled dataset, `interf test` uses that dataset's `.interf/interf.json` directly. From the project root, `interf.json` bootstraps dataset selection and the same saved truth checks are mirrored into the compiled dataset runtime contract.
 
 Maintainers can use the internal repeated-test matrix runner in [docs/test-matrix.md](./docs/test-matrix.md) for controlled workflow or model comparisons. Normal users should stay on `interf test`.
 
-## Advanced: Separate Workspaces
+## Advanced: Multiple Datasets
 
-Most folders only need one workspace.
+Most projects only need one dataset entry.
 
-Create another only when you want a different compiled setup with different checks, for example:
+Add another only when you want a different dataset folder, focus, or set of truth checks, for example:
 
 - general folder understanding
 - finance reporting
 - board prep
 - diligence review
 
-Why create another one:
+Why add another:
 
 - it keeps a separate set of truth checks
-- it gives that job its own compiled output under `interf/workspaces/<name>/`
-- it lets you test that job separately
+- it gives that dataset its own compiled output under `interf/<dataset>/compiled/`
+- it lets you test that dataset separately
 
 ## Advanced: Compile Loops
 
@@ -212,14 +214,14 @@ The workflow is the right surface for that kind of improvement because it is:
 
 Interf Compiler preserves the workflow-improvement shell, the workflow-before / workflow-after snapshots, the failed stage shells, and the saved test runs from each loop so you can inspect exactly what the loop reviewed and changed.
 
-Example workspace config:
+Example `interf.json`:
 
 ```jsonc
 {
-  "workspaces": [
+  "datasets": [
     {
       "name": "cbre-chart-sanity",
-      "max_attempts": 3, // retry compile + test for the same workflow until this workspace passes or hits this limit
+      "max_attempts": 3, // retry compile + test for the same workflow until this dataset passes or hits this limit
       "max_loops": 2, // workflow-editing loops after retries fail
       "checks": [
         {
@@ -232,7 +234,7 @@ Example workspace config:
 }
 ```
 
-Use the normal workspace retry and loop controls first. Maintainers can use the internal repeated-test runner when they want controlled comparisons across workflows, compile profiles, or models.
+Use the normal retry and loop controls first. Maintainers can use the internal repeated-test runner when they want controlled comparisons across workflows, compile profiles, or models.
 
 ## Use It With Your Agent
 
@@ -243,11 +245,11 @@ Paste something like this into your agent:
 ```text
 Install @interf/compiler, run `interf` in this folder, and use the local agent executor.
 
-If `interf.config.json` is missing, draft one workspace with a few truth checks this agent should be able to answer from this dataset and add the expected answers for me to confirm.
+If `interf.json` is missing, draft one dataset entry with a few truth checks this agent should be able to answer from the selected dataset and add the expected answers for me to confirm.
 
-Then run a raw baseline if helpful, compile the workspace, and run `interf test`.
+Then run a files-as-is baseline if helpful, compile the dataset, and run `interf test`.
 
-Tell me whether the compiled workspace passes the truth checks, and only recommend it if it does.
+Tell me whether the compiled dataset passes the truth checks, and only recommend it if it does.
 ```
 
 ## Custom Workflows
@@ -273,12 +275,12 @@ Workflow docs live in [docs/workflow-spec.md](./docs/workflow-spec.md).
 
 ## Core Commands
 
-- `interf` = open the root-folder wizard
-- `interf init` = alias for the root-folder wizard
-- `interf create workspace` = create another compiled workspace when you need one
+- `interf` = open the project-root wizard
+- `interf init` = alias for the project-root wizard
+- `interf create dataset` = add another dataset entry when you need one
 - `interf create workflow` = create a reusable local seed workflow
-- `interf compile` = build a selected workspace for the current folder
-- `interf test` = compare the raw files and a compiled workspace on saved truth checks
+- `interf compile` = build a selected compiled dataset for the current project
+- `interf test` = compare files as-is and a compiled dataset on saved truth checks
 - `interf doctor` = check local executor setup
 - `interf verify <check>` = run deterministic checks on major workflow steps
 - `interf reset <scope>` = remove generated state while keeping source files

package/builtin-workflows/interf/README.md

@@ -1,19 +1,19 @@
 # Interf Compiler (Recommended)
 
-Interf Compiler's default methodology: summarize source-grounded evidence, structure the cross-file layer, then shape the final workspace around its focus and saved truth checks.
+Interf Compiler's default methodology: summarize source-grounded evidence, structure the cross-file layer, then shape the final compiled dataset around its focus and saved truth checks.
 
 ## Package
 
 - `workflow.json` = stage graph, compiler API target, and compile contract mapping
-- `workspace.schema.json` = deterministic workspace output shape
+- `compiled.schema.json` = deterministic compiled-dataset output shape
 - `improve/`, `compile/stages/`, and `use/query/` = human-readable authoring docs
 - Portable workflow packages are standalone: explicit stages, schema, and docs live together in this folder
 - Interf Compiler projects native agent shells from these docs for query use, stage execution, and workflow-improvement loops
 
 ## Stages
 
-- `summarize` — Turn source files into per-file summaries. (workspace-file-evidence; reads: raw, runtime; writes: summaries)
-- `structure` — Build the cross-file knowledge structure from the summaries. (workspace-knowledge-structure; reads: summaries, runtime; writes: knowledge-entities, knowledge-claims, knowledge-indexes)
-- `shape` — Shape the final workspace around the saved focus and truth checks. (workspace-query-shape; reads: raw, summaries, knowledge-entities, knowledge-claims, knowledge-indexes, runtime; writes: knowledge-indexes, home)
+- `summarize` — Turn source files into per-file summaries. (compiled-file-evidence; reads: raw, runtime; writes: summaries)
+- `structure` — Build the cross-file knowledge structure from the summaries. (compiled-knowledge-structure; reads: summaries, runtime; writes: knowledge-entities, knowledge-claims, knowledge-indexes)
+- `shape` — Shape the final compiled dataset around the saved focus and truth checks. (compiled-query-shape; reads: raw, summaries, knowledge-entities, knowledge-claims, knowledge-indexes, runtime; writes: knowledge-indexes, home)
 
-This package is the built-in seed for `interf`. Interf Compiler copies or materializes it into `.interf/workflow/` and runs that workspace-local package directly.
+This package is the built-in seed for `interf`. Interf Compiler copies or materializes it into `.interf/workflow/` and runs that local package directly.

package/builtin-workflows/interf/compile/stages/shape/SKILL.md

@@ -1,12 +1,12 @@
 # Shape
 
-Shape the final workspace around the saved focus and truth checks.
+Shape the final compiled dataset around the saved focus and truth checks.
 
-Contract type: `workspace-query-shape`
+Contract type: `compiled-query-shape`
 
 ## Requirements
 
-- Use the workspace focus plus saved truth-check question text to shape `home.md` and retrieval routes.
+- Use the compiled focus plus saved truth-check question text to shape `home.md` and retrieval routes.
 - Rewrite `home.md` into a real entrypoint note. Do not leave the scaffold `Not yet compiled.` placeholder in place.
 - When a chart-derived value is approximate, use a bounded range instead of a pseudo-exact number.
 - Match the granularity of the visible axis labels or bands. Do not invent finer precision than the chart supports.
@@ -15,14 +15,14 @@ Contract type: `workspace-query-shape`
 - If a mark touches or nearly touches a labeled gridline, anchor the answer at that gridline or the immediately adjacent half-band.
 - Do not widen a chart-derived range across multiple visible bands unless the chart genuinely supports that uncertainty.
 - When you settle on a bounded chart read, keep that same band consistent across `home.md`, focused indexes, and claim/entity notes for that metric and year.
-- Do not copy expected answers into the workspace.
+- Do not copy expected answers into the compiled dataset.
 
 ## Notes
 
-- Use the workspace focus and saved truth checks to bias the final workspace toward the job it should be especially good at.
-- Do not copy expected answers into the final workspace just because the checks imply them.
+- Use the dataset focus and saved truth checks to bias the final compiled dataset toward the job it should be especially good at.
+- Do not copy expected answers into the final compiled dataset just because the checks imply them.
 - Prefer the saved summary evidence and structured notes when they already preserve the bounded chart/table reads plus provenance you need.
 - Reopen `raw/` during shaping only when the compiled layer is missing the needed value, the metric family is ambiguous, or the earlier bounded read is clearly inconsistent.
 - If a saved truth check depends on chart-derived or table-derived values, carry the final bounded reads forward into focused notes with provenance instead of repeatedly recomputing them from raw.
 - Prefer better routing, prioritization, and focused navigation over speculative synthesis.
-- Any wikilinks you add to `home.md` or indexes must resolve to real workspace note basenames or explicit relative paths.
+- Any wikilinks you add to `home.md` or indexes must resolve to real compiled note basenames or explicit relative paths.

package/builtin-workflows/interf/compile/stages/structure/SKILL.md

@@ -2,7 +2,7 @@
 
 Build the cross-file knowledge structure from the summaries.
 
-Contract type: `workspace-knowledge-structure`
+Contract type: `compiled-knowledge-structure`
 
 ## Requirements
 
@@ -14,5 +14,5 @@ Contract type: `workspace-knowledge-structure`
 - Bias structure toward canonical entities, claims, timelines, and stable indexes.
 - Use taxonomy and ontology only as means to improve retrieval, navigation, and evidence tracking.
 - For small datasets, prefer a minimal stable substrate over exhaustive graph sprawl.
-- When you add wikilinks, target real workspace notes by exact basename or explicit relative path. Do not invent title-style links unless that exact title is also a declared note label or alias.
+- When you add wikilinks, target real compiled notes by exact basename or explicit relative path. Do not invent title-style links unless that exact title is also a declared note label or alias.
 - For summary references, prefer explicit links like `[[summaries/<file-stem>]]` or plain code paths. For knowledge notes, prefer the final filename stem under `knowledge/`.

package/builtin-workflows/interf/compile/stages/summarize/SKILL.md

@@ -2,7 +2,7 @@
 
 Turn source files into per-file summaries.
 
-Contract type: `workspace-file-evidence`
+Contract type: `compiled-file-evidence`
 
 ## Requirements
 

package/builtin-workflows/interf/{workspace.schema.json → compiled.schema.json}

@@ -1,8 +1,8 @@
 {
-  "kind": "workspace-schema",
+  "kind": "compiled-schema",
   "version": 1,
-  "target_type": "workspace",
-  "label": "Interf Compiler (Recommended) workspace schema",
+  "target_type": "compiled",
+  "label": "Interf Compiler (Recommended) compiled dataset schema",
   "zones": [
     {
       "id": "raw",
@@ -10,7 +10,7 @@
       "kind": "directory",
       "required": true,
       "owned_by": [],
-      "description": "Workspace-local raw snapshot copied from the dataset for direct evidence and verification."
+      "description": "Dataset-local raw snapshot copied from the dataset for direct evidence and verification."
     },
     {
       "id": "summaries",
@@ -61,7 +61,7 @@
       "owned_by": [
         "shape"
       ],
-      "description": "Primary entrypoint note for agents using the compiled workspace."
+      "description": "Primary entrypoint note for agents using the compiled dataset."
     },
     {
       "id": "runtime",

package/builtin-workflows/interf/improve/SKILL.md

@@ -3,13 +3,13 @@
 Workflow: interf
 
 This file is the editable authoring source for Interf Compiler's generated native workflow-improver shell.
-The improver edits this workspace-local package directly.
+The improver edits this local package directly.
 
 Default loop:
 1. Read the loop context first.
 2. Review preserved stage shells, runtime logs, and saved test runs from failed attempts.
-3. Edit only the local workflow package for this workspace to create a better workflow variation for this dataset.
-4. Keep `workflow.json`, `workspace.schema.json`, and any changed stage docs aligned.
+3. Edit only the local workflow package for this compiled dataset to create a better workflow variation for this dataset.
+4. Keep `workflow.json`, `compiled.schema.json`, and any changed stage docs aligned.
 
 Guardrails:
 - do not edit truth checks, test specs, or raw dataset files

package/builtin-workflows/interf/use/query/SKILL.md

@@ -22,7 +22,7 @@ Answering rule:
 - use an upper-half or lower-half band only when the mark clearly sits there.
 - if a mark touches or nearly touches a labeled gridline, anchor the answer at that gridline or the immediately adjacent half-band.
 - do not widen a chart-derived range across multiple visible bands unless the chart genuinely supports that uncertainty.
-- if multiple compiled notes mention the same chart read, keep the answer consistent with the most focused workspace note rather than synthesizing a new midpoint or shifted band
+- if multiple compiled notes mention the same chart read, keep the answer consistent with the most focused compiled note rather than synthesizing a new midpoint or shifted band
 - when the compiled layer is insufficient, verify in `raw/` and then answer
 
-You can edit this file to bias manual question-answering behavior for this workspace.
+You can edit this file to bias manual question-answering behavior for this compiled dataset.

package/builtin-workflows/interf/workflow.json

@@ -1,18 +1,18 @@
 {
   "id": "interf",
-  "type": "workspace",
+  "type": "compiled",
   "compiler_api": {
-    "kind": "workspace",
+    "kind": "compiled",
     "version": 1
   },
   "label": "Interf Compiler (Recommended)",
-  "hint": "Interf Compiler's default methodology: summarize source-grounded evidence, structure the cross-file layer, then shape the final workspace around its focus and saved truth checks.",
+  "hint": "Interf Compiler's default methodology: summarize source-grounded evidence, structure the cross-file layer, then shape the final compiled dataset around its focus and saved truth checks.",
   "stages": [
     {
       "id": "summarize",
       "label": "Summarize",
       "description": "Turn source files into per-file summaries.",
-      "contract_type": "workspace-file-evidence",
+      "contract_type": "compiled-file-evidence",
       "skill_dir": "summarize",
       "reads": [
         "raw",
@@ -22,23 +22,25 @@
         "summaries"
       ],
       "acceptance": {
-        "artifacts_exist": [
-          ".interf/runtime/inventory.json"
+        "stage_truthy": [
+          "finished_at"
         ],
-        "state_truthy": [
-          "last_summarize",
-          "inventory_complete"
+        "zone_counts_at_least_counts": {
+          "summaries": "source_total"
+        },
+        "markdown_frontmatter_valid_zones": [
+          "summaries"
         ],
-        "state_at_least_counts": {
-          "summarized": "expected_summary_total"
-        }
+        "markdown_abstract_valid_zones": [
+          "summaries"
+        ]
       }
     },
     {
       "id": "structure",
       "label": "Structure",
       "description": "Build the cross-file knowledge structure from the summaries.",
-      "contract_type": "workspace-knowledge-structure",
+      "contract_type": "compiled-knowledge-structure",
       "skill_dir": "structure",
       "reads": [
         "summaries",
@@ -53,20 +55,22 @@
         "artifacts_exist": [
           "knowledge/indexes"
         ],
-        "state_truthy": [
-          "last_structure",
-          "inventory_complete"
+        "stage_truthy": [
+          "finished_at"
         ],
-        "state_at_least_counts": {
-          "structured": "summary_total"
-        }
+        "wikilinks_valid_in_zones": [
+          "summaries",
+          "knowledge-entities",
+          "knowledge-claims",
+          "knowledge-indexes"
+        ]
       }
     },
     {
       "id": "shape",
       "label": "Shape",
-      "description": "Shape the final workspace around the saved focus and truth checks.",
-      "contract_type": "workspace-query-shape",
+      "description": "Shape the final compiled dataset around the saved focus and truth checks.",
+      "contract_type": "compiled-query-shape",
       "skill_dir": "shape",
       "reads": [
         "raw",
@@ -84,13 +88,20 @@
         "artifacts_exist": [
           "home.md"
         ],
-        "state_truthy": [
-          "last_shape",
-          "inventory_complete"
+        "stage_truthy": [
+          "finished_at"
+        ],
+        "wikilinks_valid_in_zones": [
+          "summaries",
+          "knowledge-entities",
+          "knowledge-claims",
+          "knowledge-indexes",
+          "home"
         ],
-        "state_at_least_counts": {
-          "shaped": "summary_total",
-          "compiled": "summary_total"
+        "artifacts_must_not_contain": {
+          "home.md": [
+            "Not yet compiled."
+          ]
         }
       }
     }
@@ -106,15 +117,15 @@
       "Bias structure toward canonical entities, claims, timelines, and stable indexes.",
       "Use taxonomy and ontology only as means to improve retrieval, navigation, and evidence tracking.",
       "For small datasets, prefer a minimal stable substrate over exhaustive graph sprawl.",
-      "When you add wikilinks, target real workspace notes by exact basename or explicit relative path. Do not invent title-style links unless that exact title is also a declared note label or alias.",
+      "When you add wikilinks, target real compiled notes by exact basename or explicit relative path. Do not invent title-style links unless that exact title is also a declared note label or alias.",
       "For summary references, prefer explicit links like `[[summaries/<file-stem>]]` or plain code paths. For knowledge notes, prefer the final filename stem under `knowledge/`."
     ],
     "shape": [
-      "Use the workspace focus and saved truth checks to bias the final workspace toward the job it should be especially good at.",
-      "Do not copy expected answers into the final workspace just because the checks imply them.",
+      "Use the dataset focus and saved truth checks to bias the final compiled dataset toward the job it should be especially good at.",
+      "Do not copy expected answers into the final compiled dataset just because the checks imply them.",
       "If a saved truth check depends on chart-derived or table-derived values, verify the needed evidence in `raw/` while shaping and write focused notes that preserve bounded values plus provenance.",
       "Prefer better routing, prioritization, and focused navigation over speculative synthesis.",
-      "Any wikilinks you add to `home.md` or indexes must resolve to real workspace note basenames or explicit relative paths."
+      "Any wikilinks you add to `home.md` or indexes must resolve to real compiled note basenames or explicit relative paths."
     ]
   }
 }

package/dist/commands/check-draft.d.ts

@@ -0,0 +1,19 @@
+import type { WorkflowExecutor } from "../lib/executors.js";
+import type { SourceTruthCheck } from "../lib/schema.js";
+export declare function buildTruthCheckDraftPrompt(options: {
+    datasetName: string;
+    datasetPath: string;
+    about?: string;
+    outputPath: string;
+    targetCount: number;
+}): string;
+export declare function draftTruthChecks(options: {
+    datasetName: string;
+    datasetPath: string;
+    about?: string;
+    executor: WorkflowExecutor;
+    targetCount?: number;
+}): Promise<{
+    checks: SourceTruthCheck[] | null;
+    error?: string;
+}>;