diff --git a/README.md b/README.md index 9e92843..9f0dfcb 100644 --- a/README.md +++ b/README.md @@ -18,6 +18,7 @@ Start with: - `docs/evaluation-and-inspection.md` - `docs/reference-pilot-decision.md` - `docs/markitect-main-scope-assessment.md` +- `docs/orthogonal-successor-roadmap.md` - `infospaces/bootstrap-pilot/` - `workplans/` diff --git a/docs/markitect-tool-and-infospace-replacement-assessment.md b/docs/markitect-tool-and-infospace-replacement-assessment.md new file mode 100644 index 0000000..2c4cd67 --- /dev/null +++ b/docs/markitect-tool-and-infospace-replacement-assessment.md @@ -0,0 +1,224 @@ +# Markitect Tool And Infospace Replacement Assessment + +Date: 2026-05-14 + +## Questions + +1. Does `infospace-bench` use `markitect-tool`? +2. Can `infospace-bench` replace the infospace features that were present in + `markitect-project` / `markitect-main`? + +## Short Answer + +`infospace-bench` does **not** currently use `markitect-tool`. + +`infospace-bench` can replace the **foundation** of the old infospace feature +set, but it cannot yet replace the full `markitect-project` infospace surface. +It has a clean file-backed lifecycle, artifact manifest, evaluation result +models, basic deterministic collection checks, viability thresholding, +relationship summaries, and a small reference pilot. The legacy project still +has substantially more mature Markdown parsing, entity extraction, schema +validation, LLM pipeline execution, classification, metrics history, relation +parsing, graph export, and CLI views. + +## Current `infospace-bench` State + +Implemented and tested: + +- `create_infospace()`, `load_infospace()`, `add_artifact()` +- `infospace.yaml` plus `artifacts/index.yaml` +- JSON CLI commands: `create`, `inspect`, `add-artifact`, `export` +- Structured `InfospaceError` +- Evaluation objects: `ScoreEntry`, `EntityEvaluation`, `MetricValue`, + `EvaluationSnapshot`, snapshot diffs +- Baseline collection metrics: + - `redundancy_ratio` + - `coverage_ratio` + - `coherence_components` + - `consistency_cycles` + - `granularity_entropy` +- Viability threshold checks +- Relationship summaries and Mermaid export +- `infospaces/bootstrap-pilot` + +Current test status: `14 passed`. + +Current dependency declaration: + +```toml +dependencies = ["PyYAML>=6"] +``` + +There is no import of `markitect_tool`, no package dependency on +`markitect-tool`, and no adapter layer around its APIs. + +## Current `markitect-tool` Relevance + +`markitect-tool` is the syntax-layer successor to the Markdown tooling from +`markitect-main`. It already exposes several surfaces that `infospace-bench` +should use instead of reimplementing: + +- Markdown parsing: + - `parse_markdown()` + - `parse_markdown_file()` + - `Document`, `Heading`, `Section`, `ContentBlock` +- Schema validation: + - `validate_markdown_file()` + - `validate_document()` + - `load_schema_file()` +- Contracts and diagnostics: + - document contracts + - validation diagnostics + - metric collection +- Query, cache, reference, processor, workflow, and generation primitives + +This matches the intended boundary in `INTENT.md`: `markitect-tool` makes +Markdown structured and manipulable; `infospace-bench` makes applied knowledge +spaces concrete and meaningful. + +## Legacy `markitect-project` Infospace Surface + +The legacy infospace package in `markitect-main/markitect/infospace/` includes: + +- Entity metadata parsing from Markdown entity files +- Entity schema and compliance validation +- Infospace config loading/saving, including schema registry, pipeline config, + competency questions, directories, and viability thresholds +- Per-entity LLM evaluation prompt construction, response parsing, and batch + execution +- Evaluation file I/O, snapshot history, and history diffing +- Collection checks for redundancy, coverage, coherence, consistency, and + granularity +- Metrics file writing and history tracking +- Classification models and classification summaries +- Relation triplet parsing +- Entity/relation graph construction and export +- Source processing pipeline over `infospace.yaml` stages +- CLI commands including status, entities, chapters, evaluate, eval-summary, + relations, classify, classify-summary, classify-links, viability, check, + history, history-diff, bind-discipline, process, stale-mappings, and graph +- The large `examples/infospace-with-history` reference experiment + +## Capability Comparison + +| Capability | `infospace-bench` today | Legacy `markitect-project` | Replacement status | +| --- | --- | --- | --- | +| File-backed infospace layout | Yes | Partial/different | Replaceable | +| Config model | Basic | Rich | Partial | +| Artifact manifest | Yes | Entity/output directories | New baseline, not equivalent | +| Entity Markdown parsing | No | Yes | Missing | +| Markdown syntax parsing via `markitect-tool` | No | Legacy `markitect.core` | Missing integration | +| Schema validation | No | Yes | Missing; should use `markitect-tool` | +| Structured errors | Yes | Mixed CLI exits/exceptions | Improved baseline | +| Evaluation result models | Yes | Yes | Mostly replaceable | +| Evaluation I/O/history | No | Yes | Missing | +| LLM evaluation pipeline | No | Yes | Missing; should route through lower-layer adapters | +| Collection metrics | Basic deterministic | Richer entity/graph based checks | Partial | +| Viability thresholds | Yes | Yes | Basic replacement | +| Relationship summary | Basic manifest edges | Relation files, classifications, graph export | Partial | +| Mermaid graph export | Basic | Richer typed graph export | Partial | +| Classification | No | Yes | Missing | +| Source processing pipeline | No | Yes | Missing | +| Reference pilot | Small bootstrap pilot | Large Wealth of Nations/VSM pilot | Partial | +| CLI surface | Minimal | Broad | Not replaceable yet | + +## Assessment + +`infospace-bench` is correctly positioned as the successor, but it is still in +the early replacement phase. It is valuable because it has cleaner boundaries +than `markitect-project`: it does not carry old Markdown parser code, prompt +runtime infrastructure, asset management, GraphQL experiments, or platform +concerns. + +That boundary clarity is also why it is not a full replacement yet. The missing +work is not just code volume; it is the application-layer integration between +real Markdown artifacts, schemas/contracts, workflow execution, evaluation +history, and graph inspection. + +## Recommended Replacement Path + +### Phase 1: Integrate `markitect-tool` + +Add an explicit dependency on `markitect-tool` and introduce a thin adapter +module in `infospace-bench`, for example: + +```text +src/infospace_bench/markdown_adapter.py +``` + +The adapter should expose only application-level operations needed by +infospaces: + +- parse artifact Markdown into a structured document +- extract heading-led sections +- validate an artifact against a configured schema/contract +- return diagnostics in `InfospaceError`-compatible shapes + +Do not expose the whole `markitect-tool` API through `infospace-bench`. + +### Phase 2: Replace Legacy Entity Parsing And Validation + +Reimplement the useful parts of `markitect/infospace/entity_parser.py`, +`schema.py`, and `validator.py` on top of `markitect-tool` parsed documents and +schema/contract validation. + +Acceptance target: + +- migrate a small entity fixture from `examples/infospace-with-history` +- parse entity metadata +- validate required sections +- emit structured diagnostics + +### Phase 3: Add Evaluation History I/O + +Promote the current evaluation dataclasses into persistent artifacts: + +- write/read entity evaluation files +- write/read snapshots +- append/read history +- diff snapshots from disk +- merge collection metrics with per-artifact evaluation scores + +### Phase 4: Rebuild Relation And Graph Features + +Reimplement relation parsing and typed graph export, again using +`markitect-tool` for Markdown structure and keeping graph semantics in +`infospace-bench`. + +Acceptance target: + +- parse relation artifacts +- build an artifact/entity graph +- export Mermaid/DOT +- filter by relationship type or artifact id + +### Phase 5: Reintroduce Workflow Execution + +Rebuild the old `SourcePipeline` as an application workflow over explicit +artifact manifests and workflow definitions. Deterministic Markdown transforms +should use `markitect-tool`; LLM/provider behavior should go through +`llm-connect` or the eventual engine boundary, not direct legacy prompt code. + +### Phase 6: Migrate A Pruned Legacy Pilot + +Migrate a small, representative slice of +`markitect-main/examples/infospace-with-history`: + +- one or two source chapters +- schemas/contracts +- a few generated entities +- relation examples +- expected evaluation/metrics outputs + +This should become the real proof that `infospace-bench` can replace the old +infospace features. + +## Conclusion + +`infospace-bench` should become the replacement for `markitect-project` +infospace features, but the replacement is not complete today. + +The next decisive step is to make `markitect-tool` the Markdown/syntax +dependency of `infospace-bench`. After that, replacement should proceed through +entity parsing, schema/contract validation, evaluation history, relation graph +features, workflow execution, and finally migration of a pruned legacy pilot. diff --git a/docs/orthogonal-successor-roadmap.md b/docs/orthogonal-successor-roadmap.md new file mode 100644 index 0000000..01aeb27 --- /dev/null +++ b/docs/orthogonal-successor-roadmap.md @@ -0,0 +1,93 @@ +# Orthogonal Successor Roadmap + +Date: 2026-05-14 + +## Purpose + +This roadmap explains how `infospace-bench`, `markitect-tool`, and +`kontextual-engine` should together replace the relevant functionality of the +original `markitect-project` without recreating a monolith. + +## Orthogonal Roles + +| Repository | Layer | Owns | Must not own | +| --- | --- | --- | --- | +| `markitect-tool` | Syntax | Markdown parsing, document structure, contracts, validation, references, transformations, local query/cache primitives, CLI/library tooling | Concrete knowledge-space projects, durable operational state, domain workflows | +| `kontextual-engine` | System | Persistent asset identity, ingestion, metadata, relationships, retrieval, governed transformation, workflow execution, APIs, permissions, auditability | Markdown-specific syntax rules, one domain application, final knowledge-space methodology | +| `infospace-bench` | Application | Concrete infospaces, artifact manifests, evaluation methodology, inspection reports, reference experiments, applied workflows, migration pilots | Low-level Markdown tooling, general runtime/orchestration platform, reusable engine primitives | + +## Replacement Principle + +The old `markitect-project` combined syntax, runtime, application, examples, +and experiments in one repo. The successor architecture should preserve the +useful behaviors by relocating them to the correct layer: + +- Markdown document mechanics move to `markitect-tool`. +- Persistence, retrieval, orchestration, governance, and agent-safe operations + move to `kontextual-engine`. +- Infospace definitions, experiments, quality methodology, concrete pilots, + and applied inspection workflows live in `infospace-bench`. + +`infospace-bench` should therefore replace the old infospace feature surface as +an **application composition** of the two lower layers, not as a direct code +copy. + +## Legacy Feature Placement + +| Old `markitect-project` feature | New home | Notes | +| --- | --- | --- | +| Markdown AST parsing and section extraction | `markitect-tool` | `infospace-bench` consumes via adapter. | +| Entity/relation Markdown shape validation | `markitect-tool` + `infospace-bench` | Generic contract validation in tool; infospace-specific contract selection in bench. | +| Infospace config and project layout | `infospace-bench` | Concrete application artifact. | +| Entity and relation domain models | `infospace-bench` | Application-level knowledge semantics. | +| Collection checks and viability thresholds | `infospace-bench` | Methodology belongs with applied infospaces. | +| Metrics history and evaluation reports | `infospace-bench` initially; `kontextual-engine` later for durable storage | File-backed first, engine-backed when needed. | +| Source processing pipelines | `infospace-bench` definitions; `markitect-tool` transforms; `kontextual-engine` orchestration | Keep workflow intent separate from runtime. | +| LLM-assisted evaluation/generation | `infospace-bench` workflow contracts; provider abstraction outside or lower layer | No vendor lock-in. | +| Asset identity, provenance, retrieval, workflow runs | `kontextual-engine` | `infospace-bench` should integrate, not reimplement. | +| Reference experiments such as Wealth of Nations/VSM | `infospace-bench` | Concrete pilot and acceptance corpus. | + +## Workplan Set + +The following `infospace-bench` workplans establish the path: + +1. `IB-WP-0005` — Orthogonal successor architecture and feature map +2. `IB-WP-0006` — `markitect-tool` adapter and Markdown artifact validation +3. `IB-WP-0007` — Entity and relation model migration +4. `IB-WP-0008` — Evaluation history, metrics, and viability parity +5. `IB-WP-0009` — Applied workflow and generation pipeline +6. `IB-WP-0010` — `kontextual-engine` integration boundary +7. `IB-WP-0011` — Pruned legacy reference pilot migration +8. `IB-WP-0012` — Replacement readiness and CLI parity gate + +## Sequencing + +```text +IB-WP-0005 + -> IB-WP-0006 + -> IB-WP-0007 + -> IB-WP-0008 + -> IB-WP-0009 + -> IB-WP-0010 + -> IB-WP-0011 + -> IB-WP-0012 +``` + +The sequence is intentionally conservative: first prove boundaries, then add +syntax-layer integration, then migrate application semantics, then introduce +runtime/engine integration and final replacement gates. + +## Success Criteria + +The successor split is working when: + +- `infospace-bench` can run meaningful infospaces without internal Markdown + parser code. +- `infospace-bench` can optionally persist and operate infospaces through + `kontextual-engine` without becoming an engine itself. +- A pruned legacy MarkiTect infospace can be migrated and evaluated with + traceable outputs. +- Users can see which old `markitect-project` infospace commands are replaced, + reframed, delegated, or intentionally retired. +- The three repos remain independently understandable from their own + `INTENT.md` files. diff --git a/workplans/IB-WP-0005-orthogonal-successor-architecture.md b/workplans/IB-WP-0005-orthogonal-successor-architecture.md new file mode 100644 index 0000000..97e295d --- /dev/null +++ b/workplans/IB-WP-0005-orthogonal-successor-architecture.md @@ -0,0 +1,94 @@ +--- +id: IB-WP-0005 +type: workplan +title: "Orthogonal Successor Architecture" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0005-orthogonal-successor-architecture" +state_hub_workstream_id: "ce26304b-aef2-4e01-926c-0635fc7a0f9b" +--- + +# IB-WP-0005 — Orthogonal Successor Architecture + +## Goal + +Establish the explicit architecture and migration map that lets +`infospace-bench`, `markitect-tool`, and `kontextual-engine` replace the useful +parts of `markitect-project` without recreating its mixed responsibilities. + +## Context + +The three `INTENT.md` files define an orthogonal stack: + +- `markitect-tool`: Markdown syntax and transformation foundation +- `kontextual-engine`: persistent, governed, retrievable, operational knowledge + engine +- `infospace-bench`: concrete applied infospaces and evaluation workflows + +This workplan creates the durable successor map and keeps future work inside +those boundaries. + +## Tasks + +### T01 — Feature inventory from legacy `markitect-project` + +```task +id: IB-WP-0005-T01 +status: todo +priority: high +state_hub_task_id: "10b456fa-fc07-43cc-8a83-7382cfab57a9" +``` + +- Inventory legacy infospace CLI commands, modules, examples, and outputs +- Classify each feature as migrate, delegate, reimplement, defer, or retire +- Record the target repo for each retained feature + +### T02 — Boundary and interface map + +```task +id: IB-WP-0005-T02 +status: todo +priority: high +state_hub_task_id: "f5a57259-97a1-4690-b448-c1d15668a1b9" +``` + +- Define what `infospace-bench` expects from `markitect-tool` +- Define what `infospace-bench` expects from `kontextual-engine` +- Define what remains file-backed inside `infospace-bench` + +### T03 — Replacement acceptance matrix + +```task +id: IB-WP-0005-T03 +status: todo +priority: high +state_hub_task_id: "0a4f35b4-377a-421d-8d6e-80dee467e1aa" +``` + +- Build a matrix mapping old behavior to new behavior +- Include tests, docs, CLI/API expectations, and pilot coverage for each row +- Mark clear non-goals so replacement does not become scope creep + +### T04 — State Hub alignment + +```task +id: IB-WP-0005-T04 +status: todo +priority: medium +state_hub_task_id: "5e9f9889-b50c-4353-986f-c5b473fa9fc5" +``` + +- Register this roadmap as State Hub workstreams +- Link follow-on workplans to this architecture record +- Keep progress events tied to replacement readiness + +## Acceptance + +- `docs/orthogonal-successor-roadmap.md` is complete enough to guide future work +- Legacy infospace features have a target home or explicit retirement decision +- Follow-on workplans are created and sequenced diff --git a/workplans/IB-WP-0006-markitect-tool-adapter.md b/workplans/IB-WP-0006-markitect-tool-adapter.md new file mode 100644 index 0000000..ac6561d --- /dev/null +++ b/workplans/IB-WP-0006-markitect-tool-adapter.md @@ -0,0 +1,83 @@ +--- +id: IB-WP-0006 +type: workplan +title: "Markitect Tool Adapter And Markdown Artifact Validation" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0006-markitect-tool-adapter" +state_hub_workstream_id: "713415b0-0c14-4367-8217-26c729648aec" +--- + +# IB-WP-0006 — Markitect Tool Adapter And Markdown Artifact Validation + +## Goal + +Make `markitect-tool` the syntax-layer dependency of `infospace-bench` through +a thin application adapter. + +## Tasks + +### T01 — Add dependency and adapter boundary + +```task +id: IB-WP-0006-T01 +status: todo +priority: high +state_hub_task_id: "b438be61-6d2a-44f9-b235-2b415e9f4bca" +``` + +- Add a local development dependency on `markitect-tool` +- Create `src/infospace_bench/markdown_adapter.py` +- Keep the adapter narrow: parse, section extraction, schema/contract validation, + diagnostics + +### T02 — Parse Markdown artifacts through `markitect-tool` + +```task +id: IB-WP-0006-T02 +status: todo +priority: high +state_hub_task_id: "d37d6be3-ea04-4279-a113-086ab4fb617d" +``` + +- Replace ad hoc assumptions about Markdown artifacts with parsed document + objects from `markitect-tool` +- Preserve `KnowledgeArtifact` as the application-level manifest object +- Add tests for heading extraction and frontmatter handling + +### T03 — Validate artifact contracts + +```task +id: IB-WP-0006-T03 +status: todo +priority: high +state_hub_task_id: "74a78679-4ef2-4b6b-a80c-b40119d9f90e" +``` + +- Support configured schema/contract references from `infospace.yaml` +- Return validation diagnostics in `InfospaceError`-compatible shapes +- Add tests for valid and invalid artifact fixtures + +### T04 — CLI inspection integration + +```task +id: IB-WP-0006-T04 +status: todo +priority: medium +state_hub_task_id: "99b4e2ca-d9be-40a5-8b10-0b0f3c18fb19" +``` + +- Extend `inspect` or add `validate` CLI behavior +- Keep output JSON and scriptable +- Document how `infospace-bench` delegates syntax behavior to `markitect-tool` + +## Acceptance + +- `infospace-bench` imports `markitect_tool` only through the adapter +- Markdown parsing and validation are tested through real artifact fixtures +- No low-level Markdown parser logic is introduced in `infospace-bench` diff --git a/workplans/IB-WP-0007-entity-relation-model-migration.md b/workplans/IB-WP-0007-entity-relation-model-migration.md new file mode 100644 index 0000000..3c56b8a --- /dev/null +++ b/workplans/IB-WP-0007-entity-relation-model-migration.md @@ -0,0 +1,82 @@ +--- +id: IB-WP-0007 +type: workplan +title: "Entity And Relation Model Migration" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0007-entity-relation-model-migration" +state_hub_workstream_id: "3f6f17c9-bf50-4297-9bd5-cbe1e33efa76" +--- + +# IB-WP-0007 — Entity And Relation Model Migration + +## Goal + +Reintroduce the old infospace entity and relation semantics as +application-level models on top of `markitect-tool` parsing. + +## Tasks + +### T01 — Define entity model + +```task +id: IB-WP-0007-T01 +status: todo +priority: high +state_hub_task_id: "d6c401be-ada6-4684-9186-8ae35101bfa8" +``` + +- Reimplement the useful `EntityMeta` fields from `markitect-project` +- Keep source provenance and artifact ID linkage explicit +- Add fixtures from a small legacy-style entity document + +### T02 — Parse entities from artifacts + +```task +id: IB-WP-0007-T02 +status: todo +priority: high +state_hub_task_id: "25e42321-33fe-4b84-8e95-c5308d91ad3b" +``` + +- Parse entity documents via `markitect-tool` sections +- Extract title, definition, context, domain, source grounding, and section slugs +- Return structured diagnostics for missing required sections + +### T03 — Define and parse relation model + +```task +id: IB-WP-0007-T03 +status: todo +priority: high +state_hub_task_id: "845a8ea0-50d8-4dd3-8cc3-23717195ae6f" +``` + +- Reimplement relation triplet concepts: subject, predicate, object, relation + type, evidence, feedback role +- Link relation endpoints to artifact/entity IDs +- Add tests for relation parsing and endpoint validation + +### T04 — Manifest integration + +```task +id: IB-WP-0007-T04 +status: todo +priority: medium +state_hub_task_id: "155028a2-4df7-4144-9193-74e95f6e51b1" +``` + +- Decide how entity and relation artifacts appear in `artifacts/index.yaml` +- Support listing entities and relations from an infospace +- Document the application-level model + +## Acceptance + +- Legacy-style entity and relation fixtures parse successfully +- Missing required sections fail visibly +- `infospace-bench` owns semantics while `markitect-tool` owns Markdown structure diff --git a/workplans/IB-WP-0008-evaluation-history-metrics-parity.md b/workplans/IB-WP-0008-evaluation-history-metrics-parity.md new file mode 100644 index 0000000..2d36d8d --- /dev/null +++ b/workplans/IB-WP-0008-evaluation-history-metrics-parity.md @@ -0,0 +1,81 @@ +--- +id: IB-WP-0008 +type: workplan +title: "Evaluation History And Metrics Parity" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0008-evaluation-history-metrics-parity" +state_hub_workstream_id: "f00ba036-dc97-4370-a4a5-9ac2bce7ce6f" +--- + +# IB-WP-0008 — Evaluation History And Metrics Parity + +## Goal + +Bring the current evaluation dataclasses up to practical parity with the old +infospace evaluation history and metrics behavior. + +## Tasks + +### T01 — Evaluation file I/O + +```task +id: IB-WP-0008-T01 +status: todo +priority: high +state_hub_task_id: "95b48ad3-c4d1-442c-9bc0-7591d948d23e" +``` + +- Write and read per-entity/per-artifact evaluation files +- Preserve human-readable Markdown body plus structured metadata +- Add round-trip tests + +### T02 — Snapshot history + +```task +id: IB-WP-0008-T02 +status: todo +priority: high +state_hub_task_id: "b4800ba8-5b86-44bb-bf47-e893bae36b22" +``` + +- Write, append, and read evaluation snapshot history +- Support diffing named snapshots from disk +- Add CLI support for history and history-diff behavior + +### T03 — Metrics merge and viability reports + +```task +id: IB-WP-0008-T03 +status: todo +priority: high +state_hub_task_id: "7abcbd63-0147-4ae8-85f0-4af51882f476" +``` + +- Persist latest metrics under `output/metrics` +- Merge collection metrics with evaluation-derived metrics +- Emit structured viability reports + +### T04 — Legacy metric compatibility notes + +```task +id: IB-WP-0008-T04 +status: todo +priority: medium +state_hub_task_id: "675d1d45-39d9-4ddd-9ab7-5d7de8a0f601" +``` + +- Compare old metric names and meanings to new baseline +- Document changed semantics and accepted differences +- Add fixtures that preserve critical old behavior + +## Acceptance + +- Evaluation and metrics history are inspectable, diffable, and reproducible +- Viability reports can be generated from committed files +- Old evaluation-history workflows have a clear replacement path diff --git a/workplans/IB-WP-0009-applied-workflow-generation-pipeline.md b/workplans/IB-WP-0009-applied-workflow-generation-pipeline.md new file mode 100644 index 0000000..5ddfbfa --- /dev/null +++ b/workplans/IB-WP-0009-applied-workflow-generation-pipeline.md @@ -0,0 +1,84 @@ +--- +id: IB-WP-0009 +type: workplan +title: "Applied Workflow And Generation Pipeline" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0009-applied-workflow-generation-pipeline" +state_hub_workstream_id: "e8c96f7b-f5c7-4fbb-b4dc-fcae7e9817f0" +--- + +# IB-WP-0009 — Applied Workflow And Generation Pipeline + +## Goal + +Rebuild the old source-processing pipeline as an application-level infospace +workflow that delegates deterministic Markdown work to `markitect-tool` and +keeps LLM/provider behavior behind explicit adapters. + +## Tasks + +### T01 — Workflow definition model + +```task +id: IB-WP-0009-T01 +status: todo +priority: high +state_hub_task_id: "32c1dafc-c523-4ab7-9985-0820a65be514" +``` + +- Define infospace workflow declarations in `infospace.yaml` +- Model inputs, outputs, templates, static macros, generated artifacts, and + expected evaluation steps +- Avoid embedding runtime orchestration concerns + +### T02 — Deterministic workflow runner + +```task +id: IB-WP-0009-T02 +status: todo +priority: high +state_hub_task_id: "2bb1f82b-f9a1-4d64-9de8-29a9f4eb78d0" +``` + +- Implement a file-backed runner for deterministic stages +- Use `markitect-tool` transforms/references/templates where applicable +- Emit traceable run records and output artifacts + +### T03 — Assisted generation boundary + +```task +id: IB-WP-0009-T03 +status: todo +priority: high +state_hub_task_id: "2dd1ad70-8b5a-4afc-8f63-b1db3915ff31" +``` + +- Define the provider-neutral interface for LLM-assisted stages +- Keep provider calls optional and auditable +- Route future implementation through `llm-connect` or engine-managed adapters + +### T04 — CLI workflow commands + +```task +id: IB-WP-0009-T04 +status: todo +priority: medium +state_hub_task_id: "63d34a33-63c6-45cb-8625-2e59ae0b6d57" +``` + +- Add `workflow inspect`, `workflow plan`, and deterministic `workflow run` + behavior +- Keep output scriptable +- Add reference fixtures + +## Acceptance + +- The old `process` concept is replaced by explicit infospace workflows +- Deterministic runs are testable without external services +- Assisted stages are designed without coupling to a model vendor diff --git a/workplans/IB-WP-0010-kontextual-engine-integration-boundary.md b/workplans/IB-WP-0010-kontextual-engine-integration-boundary.md new file mode 100644 index 0000000..2137510 --- /dev/null +++ b/workplans/IB-WP-0010-kontextual-engine-integration-boundary.md @@ -0,0 +1,84 @@ +--- +id: IB-WP-0010 +type: workplan +title: "Kontextual Engine Integration Boundary" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0010-kontextual-engine-integration-boundary" +state_hub_workstream_id: "0f69d4dc-b301-436c-8ccb-858a00bd2847" +--- + +# IB-WP-0010 — Kontextual Engine Integration Boundary + +## Goal + +Define and implement the boundary where concrete infospaces can use +`kontextual-engine` for durable knowledge operations without making +`infospace-bench` an engine. + +## Tasks + +### T01 — Engine capability contract + +```task +id: IB-WP-0010-T01 +status: todo +priority: high +state_hub_task_id: "f77c10cf-6ea2-44a6-af0b-f9c70860b999" +``` + +- Identify engine capabilities needed by infospaces: asset identity, + provenance, relationships, retrieval, workflow runs, permissions, audit +- Define what stays file-backed versus engine-backed +- Record assumptions against `kontextual-engine/INTENT.md` + +### T02 — Repository adapter design + +```task +id: IB-WP-0010-T02 +status: todo +priority: high +state_hub_task_id: "bd20ddaa-c37d-4ec0-af4e-45198172e6f8" +``` + +- Design an adapter interface for asset persistence and retrieval +- Provide a local file-backed implementation as the default +- Leave room for a `kontextual-engine` client implementation + +### T03 — Sync and provenance model + +```task +id: IB-WP-0010-T03 +status: todo +priority: high +state_hub_task_id: "12ffd95b-6db2-4881-bc3c-6bc4f9f3cc21" +``` + +- Define how infospace artifacts map to durable engine assets +- Preserve source path, artifact ID, version/digest, derived outputs, and + workflow provenance +- Add dry-run sync planning before mutation + +### T04 — Agent-safe operation notes + +```task +id: IB-WP-0010-T04 +status: todo +priority: medium +state_hub_task_id: "fe1031d6-0b48-4fa1-9edd-3b1908a62003" +``` + +- Define which operations require review, dry run, or rollback +- Align with engine governance and audit principles +- Document the first safe integration scenario + +## Acceptance + +- `infospace-bench` has a clear engine adapter contract +- The default remains file-backed and testable +- Engine-backed persistence is designed as integration, not repo identity diff --git a/workplans/IB-WP-0011-pruned-legacy-reference-pilot.md b/workplans/IB-WP-0011-pruned-legacy-reference-pilot.md new file mode 100644 index 0000000..48272c2 --- /dev/null +++ b/workplans/IB-WP-0011-pruned-legacy-reference-pilot.md @@ -0,0 +1,85 @@ +--- +id: IB-WP-0011 +type: workplan +title: "Pruned Legacy Reference Pilot" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0011-pruned-legacy-reference-pilot" +state_hub_workstream_id: "5bcc4fe2-a1d3-4edf-9e6e-0b2844b5b499" +--- + +# IB-WP-0011 — Pruned Legacy Reference Pilot + +## Goal + +Migrate a small representative slice of +`markitect-main/examples/infospace-with-history` into `infospace-bench` to prove +successor behavior against real legacy content. + +## Tasks + +### T01 — Select representative slice + +```task +id: IB-WP-0011-T01 +status: todo +priority: high +state_hub_task_id: "49d4865b-38b0-4994-a0f9-1cbdf718689c" +``` + +- Choose one or two source chapters or a compact equivalent fixture +- Include at least one entity, one relation, one evaluation, and one metrics + snapshot +- Avoid committing generated bulk + +### T02 — Migrate schemas/contracts and methodology + +```task +id: IB-WP-0011-T02 +status: todo +priority: high +state_hub_task_id: "3bea0589-cd48-4a12-b2c5-e8996d383195" +``` + +- Convert relevant legacy schemas into `markitect-tool` contracts or supported + validation artifacts +- Preserve metrics methodology where still applicable +- Document changes from the old experiment + +### T03 — Run successor pipeline + +```task +id: IB-WP-0011-T03 +status: todo +priority: high +state_hub_task_id: "fe012682-7af3-42a0-8d14-07685a663242" +``` + +- Load, validate, inspect, evaluate, and report on the migrated pilot +- Compare outputs against expected legacy behavior +- Capture gaps as follow-up tasks + +### T04 — Publish migration report + +```task +id: IB-WP-0011-T04 +status: todo +priority: medium +state_hub_task_id: "5a6c885f-6acb-4d18-9aff-f710423e0198" +``` + +- Add a report under the pilot's `reports/` +- Include what was replaced, what was delegated, and what remains missing +- Use the report as evidence for replacement readiness + +## Acceptance + +- A legacy-derived pilot exists under `infospaces/` +- It exercises parser, validation, entity/relation, evaluation, metrics, and + graph features +- Its migration report is explicit about parity and gaps diff --git a/workplans/IB-WP-0012-replacement-readiness-cli-parity.md b/workplans/IB-WP-0012-replacement-readiness-cli-parity.md new file mode 100644 index 0000000..a7bd625 --- /dev/null +++ b/workplans/IB-WP-0012-replacement-readiness-cli-parity.md @@ -0,0 +1,85 @@ +--- +id: IB-WP-0012 +type: workplan +title: "Replacement Readiness And CLI Parity Gate" +domain: markitect +repo: infospace-bench +status: planned +owner: markitect +topic_slug: markitect +created: "2026-05-14" +updated: "2026-05-14" +state_hub_workstream_slug: "ib-wp-0012-replacement-readiness-cli-parity" +state_hub_workstream_id: "72b6a923-cad5-450b-b658-b35a00cecd4d" +--- + +# IB-WP-0012 — Replacement Readiness And CLI Parity Gate + +## Goal + +Decide when `infospace-bench` can be treated as the replacement for the +in-scope infospace features from `markitect-project`. + +## Tasks + +### T01 — Legacy command parity table + +```task +id: IB-WP-0012-T01 +status: todo +priority: high +state_hub_task_id: "b48edb8e-b0af-4d46-9714-9830725d0773" +``` + +- Map legacy commands such as status, entities, chapters, evaluate, + eval-summary, relations, classify, viability, check, history, history-diff, + bind-discipline, process, stale-mappings, and graph +- Mark each as replaced, reframed, delegated, deferred, or retired +- Add replacement command/API examples + +### T02 — End-to-end acceptance suite + +```task +id: IB-WP-0012-T02 +status: todo +priority: high +state_hub_task_id: "12eb0f88-4483-48ad-b156-79fa7c2171b7" +``` + +- Build tests around the bootstrap pilot and pruned legacy pilot +- Cover lifecycle, validation, entity/relation parsing, evaluation history, + metrics, viability, workflow run, and export +- Keep all tests deterministic by default + +### T03 — Documentation and migration guide + +```task +id: IB-WP-0012-T03 +status: todo +priority: high +state_hub_task_id: "cd4ee529-1ca0-4214-80fc-000af5c16b11" +``` + +- Write a guide for moving legacy MarkiTect infospaces into `infospace-bench` +- Explain which functionality moved to `markitect-tool` and + `kontextual-engine` +- Include explicit non-goals + +### T04 — Replacement decision record + +```task +id: IB-WP-0012-T04 +status: todo +priority: medium +state_hub_task_id: "ca88d1c5-b83f-47c9-90d0-58cedc7ca6f7" +``` + +- Record whether the old infospace feature set is replaced enough for new work +- List residual gaps and owning repos +- Update State Hub with the decision + +## Acceptance + +- Replacement readiness is evidence-based, not aspirational +- Users have a command/API migration path +- Remaining gaps are explicitly owned by the correct repo