diff --git a/SCOPE.md b/SCOPE.md index 2c5264a..5f25789 100644 --- a/SCOPE.md +++ b/SCOPE.md @@ -1,125 +1,100 @@ # SCOPE -Reviewed: 2026-10-04 · Scope: ongoing research and a versioned knowledge base. +Reviewed: 2026-10-04 · Capability audit at `07f1f37`. -## Purpose and deliverable +## What this repository delivers -Develop a framework-independent frontend architecture pattern language for human -and agent reference, following [INTENT.md](INTENT.md). Its intended practical -outcome is an explainable path from a frontend problem and its forces to compatible -patterns and implementation options. +This is a versioned Markdown research knowledge base and a qualified frontend +architecture reference. Its purpose follows [INTENT.md](INTENT.md): help a reader +move from a problem and its forces to explainable pattern choices and implementation +questions. That outcome has been demonstrated through authored examples, but improved +real-world decisions and complete generativity have not been established. -The deliverable is a versioned Markdown knowledge base with structured metadata, -traceable evidence and transparent revision history. The language evolves through -bounded investigations and review gates; it has no final completion date. Completing -an experiment or milestone does not establish a mature language. +The product is reference material and research tooling. There is no maintained +frontend application, framework, online recommendation service or production runtime. +Research fixtures exercise bounded mechanisms; they are not implementation recipes. -## In scope +## Capabilities available now -- `canon/`: responsibilities, forces, scales, relations and the metadata contract, - including testing whether the proposed vocabulary explains contrasting cases. -- `research/`: identifiable sources, claim-level interpretations, candidate patterns, - counterexamples, pinned implementation studies and bounded executable experiments. -- `patterns/`: evidence-qualified canonical records when admission is justified; - research candidates remain separately identified until then. -- `sequences/` and `architectures/`: decision ordering, compatible configurations, - alternatives and resulting contexts, exercised through contrasting walkthroughs. -- `technologies/`: descriptive mappings from patterns to implementation approaches, - including their constraints and limits. -- `templates/`, `scripts/` and the infospace-bench adapter: authoring, metadata checks - and reproducible research evaluation. Live model execution uses llm-connect. -- `research/evolution/` and `history/`: evidence profiles, immutable snapshots, - prospective questions and effort, supersession, learning outcomes and dated - assessments. Track applicability, trustworthiness, usefulness, coherence, - maintainability and learning efficiency separately. +| Surface | What a reader or agent can do | Evidence and limit | +| --- | --- | --- | +| Human entry and two core sequences | Follow shared-record editing or offline-work decisions, alternatives, failure traces and implementation questions | [START.md](START.md), [transactional](sequences/TransactionalApplication.md), [offline](sequences/LocalFirstApplication.md); synthetic VC-01/02 guidance | +| Frozen 0.1 candidate reference | Read 17 pinned draft hypotheses (8 core, 9 extensions), 9 conditional proposed relations, classifications and evidence gaps | [Release registry](reference/releases.json), [index](reference/0.1/index.json); not an admitted canonical graph | +| Current research corpus | Inspect 18 developed candidate hypotheses with evidence profiles and retained source/runtime reviews | [Evolution report](research/evolution/EvolutionReport.md); the additional live candidate is outside frozen 0.1, no canonical admissions | +| Implementation mappings | Locate scoped mechanisms for transactional and offline recovery | [TransactionalRecovery](technologies/TransactionalRecovery.md), [OfflineRecovery](technologies/OfflineRecovery.md); no product supplies a certified complete configuration | +| Metadata and publication checks | Validate contract examples, candidate inventory/hashes, classification, evidence locators and immutable release artifacts | `make schema-test evolution-check classification-check reference-check`; checks establish structural traceability, not source truth | +| Research bench | Plan and execute bounded source investigations, retain failures, screen structure and explicitly replay compatible cached runs | [Bench adapter](research/bench/README.md); paid inference uses llm-connect and its task authorization/budget, not automatic invocation | +| Learning visibility | Read a selected retrospective ledger, prospective protocols, measured/unknown effort, immutable snapshots and comparison readiness | [ComparisonWindows.json](research/evolution/ComparisonWindows.json); 8 prospective cycles in 7 declared groups, none reaches the 3-cycle review trigger | +| Deterministic scheduled reporting | Observe retained natural daily, weekly and October 1 monthly reports from activity-core | [Receipt reconciliation](docs/evidence/2026-10-04-loop-reconciliation.json); zero enrolled consumers, dated owner health snapshot, no admitted pattern-editing executor | -These areas include intended capabilities; directory presence is not evidence that -the corresponding capability is implemented or validated. +The frozen preview and live research are separate version surfaces. Published candidate +prose is read at its corpus revision; release documents and evidence locators are read +at the packaging revision. Legitimate new research does not rewrite the old preview. -## Current capabilities and limits +## Evidence limits and unavailable capabilities -As of 2026-09-28, eighteen developed research candidates remain draft hypotheses; -none is canonically admitted. Sources and claim-level reviews, metadata contract -checks, an infospace-bench adapter and bounded runtime research fixtures exist. -Four walkthroughs are synthetic drafts or provisional studies, not validated -architecture recipes. Six further validation cases remain planned. +The four walkthroughs (VC-01/02/03/06) are synthetic drafts or provisional studies; +six validation cases are planned. The named files under `architectures/` are research +stubs, not developed or validated architecture decompositions. General, content and +collaborative sequences contain provisional scaffolding beyond the two developed core +paths. Vocabulary and catalog names do not constitute additional implemented patterns. -The frozen development pilot scored 18/24 in each presentation condition after -submitted model-review adjudication. It establishes neither a naming benefit nor -equivalence; independent human validation and decision-time measurement remain open. +The consumed development pilot scored 18/24 in each presentation condition after +model-review adjudication. It establishes neither a naming benefit nor equivalence. +Independent human scores, fresh-scenario replication and decision-time evidence remain +missing. M1/M2 remain revise/defer, and canonical admission is open. Full canonical graph +export, held-out retrieval evaluation and real-repository applicability studies retain +their recorded prerequisites. Eight disclosed preview navigation cases are development +checks; they are not held-out retrieval results. -Evolution profiles, a baseline, learning ledger, snapshots and a generated report -are implemented. Eight prospective cycles (seven effort-accounted) belong to seven different -comparison groups: there is no comparable window for a diminishing-returns claim. -Evidence types, implementation families and review provenance remain distinct. -Static source mechanisms and authored runtime fixtures do not establish complete -pattern recurrence, production fitness or independent human confirmation. +Full-contract recurrence, production fitness, accessibility conformance, native crash +and off-device recovery guarantees are not established by the scoped source studies or +authored runtime fixtures. Seven prospective cycles have positive recorded research +time; LEARN-0017's time is unknown. A matching group label is not proof of comparability, +and there is no basis for a diminishing-returns or plateau claim. -Canonical admission, M1/M2 acceptance, demonstrated generativity, full graph export, -held-out retrieval evaluation remain open. Scoped mechanism mappings are available -in the 0.1 preview; full implementation contracts remain unverified. -There is research runtime code, but no maintained frontend application or framework -is offered as the product. See the [evolution report](research/evolution/EvolutionReport.md) -for current counts and evidence limits; [REVIEW.md](REVIEW.md) preserves the initial -2026-09-23 review and is not a current capability inventory. +The capability entry and hosted-publication preparation exist, but hosted federation +registration and eligible consumer integration lack acceptance evidence. The consumer +roster is empty; eligible-task coverage and usefulness are unknown. Deterministic +collection/reporting is implemented by activity-core, while producer closeout integration, +real use plus linked outcomes, delayed-outcome refresh, admitted bounded investigation, +authenticated publication and automatic rollback remain incomplete. Reporting schedules +are not proof of a closed autonomous improvement loop. -## Research boundaries and exclusions +## Boundaries -- Do not build or operate a general frontend application, framework, router or - release platform as the deliverable. Fixtures exist to investigate claims. -- Do not rank frameworks, prescribe a universal architecture or turn the language - into a component cookbook or collection of tool-specific idioms. -- Do not treat candidate counts, source counts, passing assertions or model agreement - as maturity, independent recurrence or proof of usefulness. -- Do not infer accessibility conformance, production guarantees or upstream defects - from bounded DOM experiments or partial source inspection. -- Do not combine viability dimensions into a maturity percentage, infer historical - effort from commits, or pool incomparable studies to claim learning saturation. +Research covers framework-independent authority, addressability, projection, mutation, +recovery, interaction, composition and delivery decisions. Additional coverage must +come from useful questions, contrasting contexts and traceable evidence. Authoring, +validation and qualified reference improvements are in scope; canonical admission and +stronger evidence claims require the existing reviews. -## Work ownership and review boundaries +Do not turn the deliverable into a framework ranking, component cookbook, general +frontend runtime or universal architecture prescription. Do not infer maturity from +catalog size, fixtures, model agreement or automation definitions. Do not fabricate +human ratings, historical effort, consumer use, complete contract recurrence or +unsupported guarantees. Policy/access/budget changes in the operating loop remain +monthly human decisions; qualified reference work can continue within existing scope. -[WP-0002](workplans/FEP-WP-0002-seed-language-validation.md) delivered seed evidence and -the connected corpus (finished; M1 revise/defer). [WP-0009](workplans/FEP-WP-0009-m1-independent-validation.md) -owns independent M1 validation. [WP-0003](workplans/FEP-WP-0003-contrasting-schools.md) -owns contrasting streams, broader walkthroughs, ontology decisions and M2. -[WP-0004](workplans/FEP-WP-0004-reference-surface.md) is blocked follow-up for graph, -held-out retrieval and real-repository applicability, subject to its recorded gates. -[WP-0006](workplans/FEP-WP-0006-language-evolution.md) owns ongoing learning visibility, -review dates and comparable-cycle measurement. Actionable work stays in workplans; -this file describes boundaries, not a second backlog. +## Work and assessment ownership -[WP-0007](workplans/FEP-WP-0007-language-v01-preview.md) packages a finite 0.1 research -preview: curated candidate reference paths, two core sequences, scoped mappings and -a candidate export. This is a bounded research preview, not a replacement for M1/M2/M3. +[WP-0009](workplans/FEP-WP-0009-m1-independent-validation.md) owns the independent M1 +validation residual of finished WP-0002. [WP-0003](workplans/FEP-WP-0003-contrasting-schools.md) +owns architectural contrasts, broader walkthroughs and M2; [WP-0004](workplans/FEP-WP-0004-reference-surface.md) +owns gated canonical export, held-out retrieval and real-repository evaluation. +[WP-0006](workplans/FEP-WP-0006-language-evolution.md) owns comparable learning evidence; +[WP-0008](workplans/FEP-WP-0008-use-driven-improvement.md) owns discovery, eligible +consumer integration/outcomes and end-to-end autonomous improvement. Workplan files +are authoritative; this document is a capability inventory, not a duplicate backlog. -The [2026-09-27 scope–intent assessment](history/2026-09-27T010237+0200-scope-vs-intent.md) -records the current gaps and recommended priorities. Future assessments should -preserve that historical judgment and cite changed evidence. - -## Ecosystem reuse and operational learning - -The user-directed [WP-0008](workplans/FEP-WP-0008-use-driven-improvement.md) connects -qualified reference use to evidence-bearing consumer receipts and bounded autonomous -improvement. It owns discovery, instrumentation and execution integration; monthly -human review owns operating-policy decisions. The capability entry is prepared; -automatic collection and three activity-core reporting schedules passed scheduled -smoke checks; the first natural daily run failed after a worker image change removed -the domain resolver. The approved grant-preserving repair is deployed and all three -scheduled sink smokes pass. Retained natural daily and weekly runs and the October 1 -monthly report are now verified against State Hub receipts; that report covers -September and carries a dated owner health snapshot. See the -[reconciliation evidence](docs/evidence/2026-10-04-loop-reconciliation.json). -Hosted consumer integration and admitted pattern-editing execution remain blocked; -there are no enrolled consumers yet. -This operational loop can improve draft guidance without claiming M1/M2/M3 or -independent-human validation. See the [operating design](docs/ReuseAndImprovementLoop.md). +The [current scope–intent assessment](history/2026-10-04T084941+0200-scope-vs-intent.md) +prioritizes consumer decision/outcome evidence, independent validation and qualified +reference consumption over catalog expansion. [WP-0010](workplans/FEP-WP-0010-reference-consumption.md) +implements the bounded local consumption bridge; it does not replace empirical owners. +The [September 27 assessment](history/2026-09-27T010237+0200-scope-vs-intent.md) remains +historical evidence of the earlier judgment. ## Registration -- Repository: `frontend-patterns` -- Category: `research` -- Domain / topic: `infotech / canon` -- Workplan prefix: `FEP-WP` - -The topic groups this research with semantic coordination work; it does not imply -that the proposed language is an adopted fleet standard. +Repository `frontend-patterns` · category `research` · domain/topic `infotech / canon` +· workplan prefix `FEP-WP`. Registration does not imply an adopted fleet standard. diff --git a/history/2026-10-04T084941+0200-scope-vs-intent.md b/history/2026-10-04T084941+0200-scope-vs-intent.md new file mode 100644 index 0000000..d61f062 --- /dev/null +++ b/history/2026-10-04T084941+0200-scope-vs-intent.md @@ -0,0 +1,88 @@ +# Scope against intent — 2026-10-04 08:49:41 Europe/Berlin + +Assessor: Codex, author-model; no independent human review. Audited repository +revision `07f1f373744986a22bc4f18710de94534f40343d`, local source records, frozen +0.1 pins and the October 4 natural-report reconciliation. This assessment does not +re-probe production, execute paid inference or supply new empirical use evidence. +The original [September 27 assessment](2026-09-27T010237+0200-scope-vs-intent.md) +is preserved. [SCOPE.md](../SCOPE.md) is the refreshed capability inventory. + +## Judgment + +The repo now supplies a usable, evidence-qualified research reference for two +frontend problem classes, with unusually explicit recovery limits and immutable +publication. It still falls short of INTENT's success condition: it has not shown +that an independent practitioner can derive and apply a useful compatible +configuration to real work, or that using the language improves the decision. +The central gap is observed consumer value and independent applicability evidence, +not a shortage of candidate names or more research administration. + +## Intent-to-capability trace + +| INTENT property/question | Current evidence | Gap | +| --- | --- | --- | +| Problem → forces → choices → implementation | START, two core sequences, two scoped mappings, VC-01/02 authored decision traces | No external task/outcome chain or measured decision benefit | +| Contextual and relational choices | Eight connected core hypotheses, 9 proposed conditional relations in the pinned 0.1 index; constraints and abstentions stated | No general compatibility solver, transitive guarantee or validated architecture generation | +| Trustworthy evidence and known uses | Source locators, pinned static-code reviews, bounded runtime receipts, explicit provenance and gaps | Full-contract independent recurrence unassessed; independent human and fresh-scenario evidence absent | +| Agent-readable reference | Frozen 17-record JSON export, IDs, classification, relation conditions and immutable version registry | No executable structured lookup/citation or consumer-side receipt producer at audit start; held-out retrieval absent | +| Multi-scale architecture decomposition | Families/scales and provisional classification; four synthetic/provisional walkthroughs | Six named architecture stubs and six planned validation cases do not establish broad applicability | +| Evolvability | Eighteen live candidates, ledger, snapshots and generated readiness audit | Eight prospective cycles across seven groups; largest two with one unknown effort, no returns-review window | +| Practical continuous improvement | Seven verified natural reporting receipts, October monthly packet | Empty consumer roster; no admitted budget-enforced editor or authenticated automatic publication/rollback | + +The live corpus has 18 candidates; frozen 0.1 has 17. Publication, current research, +canonical maturity and runtime reporting are distinct surfaces. Keeping them separate +is a capability, but requires consumer tooling that carries exact pins. + +## Most relevant gaps, in priority order + +1. **A real decision and inspectable outcome.** Select an actual eligible open frontend + task, record what the language changed or failed to answer, and follow its evidence. + Without an instrumented denominator and outcomes, usefulness stays unknown. + WP-0008 T01/T02 owns this. A fixture, this repo's audit or a finished task is not a + substitute. Implementing a small local lookup/receipt bridge removes preparation + friction now; eligible selection, common-template rollout and enrollment remain + their existing acceptance acts. +2. **Independent validation of the connected core.** WP-0009 owns human scoring, + fresh atomic-criterion replication and M1 review. Model scores cannot fill the + human sheet. Preparation can proceed without inference; paid execution retains + its explicit call-budget authorization. No admission or milestone pass follows + from the proposed local tool. +3. **Reliable constrained reference consumption and abstention.** At the audit start, + consumers must manually traverse JSON and assemble version/digest pins. Add + deterministic filtering by explicit candidate, force and responsibility, retain + force costs/conditional relations and emit commit-specific locators. Missing + context and no match must not become an inferred architecture. This is qualified + development tooling, not WP-0004's gated held-out evaluation. +4. **Contrasting coverage and full-contract implementation evidence.** WP-0003/0004 + owns broader architecture cases, independent application contrasts and retrieval. + General sequence scaffolding and architecture stubs must stay qualified. Expand + only when actual use or a necessary validation question warrants it; preserve + M1/M2 gates and the paused navigation fixture. +5. **Unattended execution and comparable learning.** WP-0008 and its external owners + retain executor budgets, real improvements and automatic release/rollback; + WP-0006 retains useful comparable windows. Natural reports prove observation, + not a closed improvement loop or a learning trend. These dependencies are not + solved by adding another schedule, group label or fabricated cycle. + +## Implementation decision and workplan + +Create [FEP-WP-0010](../workplans/FEP-WP-0010-reference-consumption.md) for the finite +local bridge: accurate scope/assessment, verified pinned lookup/citation, immutable +consumer receipt preparation and disclosed end-to-end regression fixtures. Use the +existing release validator and activity-core event contract. The producer does not +assert verified origin or a helpful outcome; only the collector verifies source pins. +No service, paid provider, credential lane, fleet mandate or maturity promotion is needed. + +Keep the empirical gaps in existing live records WP-0008, WP-0009, WP-0003/0004 and +WP-0006. Add explicit handoff references before finishing WP-0010; do not replace +those gates with new duplicate tasks or hide residuals solely in this assessment. + +Acceptance is a working local consume → cite → prepare-receipt path with stable +version/corpus/packaging pins and tested abstention, tampering and immutability. +This establishes tool behavior only. Actual integration, consumer benefit, independent +validation and production autonomy remain separate evidence requirements. + +## Verification and completion record + +To be filled from implementation receipts before closeout. The capability inventory +must describe the delivered tool behavior and retain all empirical limitations. diff --git a/workplans/FEP-WP-0010-reference-consumption.md b/workplans/FEP-WP-0010-reference-consumption.md new file mode 100644 index 0000000..4e36e61 --- /dev/null +++ b/workplans/FEP-WP-0010-reference-consumption.md @@ -0,0 +1,86 @@ +--- +id: FEP-WP-0010 +type: workplan +title: "Close local reference-consumption gaps" +domain: infotech +repo: frontend-patterns +status: ready +owner: codex +topic_slug: canon +created: "2026-10-04" +updated: "2026-10-04" +--- + +# Close local reference-consumption gaps + +Requested in the October 4 scope-versus-intent review. Reviewed against `07f1f37`, +the immutable 0.1 validator/export and activity-core's schema-v1 consumer event +contract. [Assessment](../history/2026-10-04T084941+0200-scope-vs-intent.md) ranks the +remaining gaps. This plan implements a finite local consumption bridge; it does not +claim real usefulness, independent validation, canonical export or autonomous operation. + +## Reconcile actual capabilities and ranked gaps + +```task +id: FEP-WP-0010-T01 +status: done +priority: high +``` + +Update SCOPE.md from actual artifacts and record a timestamped assessment against +INTENT. Distinguish 18 live hypotheses from the frozen 17-record preview, developed +core paths from stubs, reporting from improvement and development checks from +independent/held-out evidence. Name existing owners for the most relevant gaps. + +## Implement verified pinned lookup and citation + +```task +id: FEP-WP-0010-T02 +status: todo +priority: high +``` + +Add a small stdlib CLI to filter the verified candidate preview by explicit IDs, +improving forces and responsibilities. Carry force costs, evidence limits and +conditional relations without inferring compatibility or applicability. Empty or +unknown constraints must clarify/abstain honestly. Provide commit-specific corpus +and packaging locators; never silently read moving candidate prose. Reuse the existing +release validation and fail on tampering or unavailable pins. + +## Prepare immutable consumer closeout receipts + +```task +id: FEP-WP-0010-T03 +status: todo +priority: high +``` + +Accept an explicit consumer decision/provenance input and prepare a schema-v1 event +with verified release pins, considered/selected IDs, unchanged unknown outcomes and +exact file digest/index entry. Write new files exclusively; refuse overwrite and unsafe +source-relative paths. Validate inputs before writes. Real versus synthetic is explicit; +no consumer enrollment, fabricated real outcome, arbitrary feedback execution or +producer claim of verified collector origin. Match activity-core's existing event +contract instead of creating a second collection service. + +## Verify the bridge and hand remaining gaps to live owners + +```task +id: FEP-WP-0010-T04 +status: todo +priority: high +``` + +Run disclosed synthetic lookup/citation/receipt cases, including unsupported/no-match, +missing context, unknown IDs, changed live research, tampered release, invalid provenance, +selection/action mismatch, delayed follow-up and duplicate writes. Verify generated +receipts with the actual activity-core validator and document exact owner revision. +Provide consumer commands in existing entry points. No model call or production +mutation is required. Run repository checks and record limitations. + +Before finishing, link delivered bridge and residual acceptance to existing WP-0008 +T01/T02 (real consumer/template/enrollment/outcomes), WP-0009 (human/fresh validation), +WP-0003/0004 (broader/gated applicability) and WP-0006 (comparable windows). Add live +record references there. This plan may finish its local deliverable while the empirical +owners remain open; do not claim those gaps closed or leave actionable residuals only +in prose/history.