From 6e6baabaf45d06cff153c1276d2ae45ae0b8938d Mon Sep 17 00:00:00 2001 From: Erin Spencer Date: Sun, 16 Aug 2026 21:11:09 -0700 Subject: [PATCH] docs: restore construction and evaluation boundary --- .agents/skills/README.md | 2 +- .agents/skills/the-interdependency/SKILL.md | 47 +++++++++++++-- AGENTS.md | 19 ++++++ docs/architecture.md | 37 ++++++++++-- docs/work-graphs/repository-plan-report.json | 63 ++++++++++++-------- 5 files changed, 132 insertions(+), 36 deletions(-) diff --git a/.agents/skills/README.md b/.agents/skills/README.md index dbb8be6..3dcc2d7 100644 --- a/.agents/skills/README.md +++ b/.agents/skills/README.md @@ -3,7 +3,7 @@ This directory contains repo-local copies of canonical skills from `The-Interdependency/skill-lib`. -Source commit: `6ef2e4c123225f9db20e5230e5894c9c86b42ee6` +Source commit: `b4234ca29529f56526541df8deb58c2c19570792` Repo-local copies are not the source of truth. Edit `skill-lib` first, then propagate from the canonical source. diff --git a/.agents/skills/the-interdependency/SKILL.md b/.agents/skills/the-interdependency/SKILL.md index 627555a..72f519c 100644 --- a/.agents/skills/the-interdependency/SKILL.md +++ b/.agents/skills/the-interdependency/SKILL.md @@ -18,6 +18,7 @@ description: Protocol and workflow for all tasks involving The Interdependency o ## Core Doctrine - **Structure preservation first**: Before any summarization, compression, decision, or output, preserve the complete relational structure, variables, topology, epistemic status (declared / implemented / inferred / hmmm), distinct layers (lived experience vs formal claims vs emotional), and explicitly mark all unresolveds. This follows the org's neurodivergence-preserving interaction principles. +- **METAPAT consultation gate**: Consult current `The-Interdependency/metapat` before committing a conceptual choice when the task must decide which distinctions, relations, boundaries, transformations, scales, or cross-domain correspondences should organize downstream work. METAPAT consultation is also required when an unresolved conceptual choice would constrain architecture, semantics, measurement, ontology, or later falsifiable claims. Do not consult METAPAT merely to execute an already-fixed implementation, run tests, repair syntax, move data, or apply a relation whose meaning and boundary are already established. METAPAT is the source of truth for its own doctrine; skill-lib routes to it and must not duplicate a frozen theory snapshot. - **EDCMBONE transcript assembly & analysis**: When the task involves assembling or analyzing transcripts (e.g. for EDCMBONE / Energy Dissonance Circuit Model Bound Operator Numerical Evaluation), apply the established EDCMBONE lens: map energy flows and dissonance circuits, compute/report F-loss metrics (fidelity, deletion, inversion, collapse detection), tag F1–F6 failure modes, segment for cognitive accessibility (especially neurodivergent readers), and preserve transcript topology. Do not improvise assembly; extend or adhere to patterns from the edcmbone repository. - **Code writing standards**: When writing or modifying code that touches The-Interdependency: - Use msdmd self-declaration blocks (`# === BLOCK_NAME ===` ... `# === END BLOCK_NAME ===`) wherever the module fits an existing or new metadata skill. @@ -32,13 +33,44 @@ description: Protocol and workflow for all tasks involving The Interdependency o - **Usage guidance requirement**: Every code file, SKILL.md update, README change, research summary, or artifact produced under this skill **must contain clear, actionable usage guidance**. This is non-negotiable for accessibility, onboarding, and reducing signal loss. - **Research & canon alignment**: Ground all claims in source-backed canon (cross-load `canon` skill). Use `char-compress` for context handoff. Leave genuine uncertainty as `hmmm`. +## METAPAT consultation test + +Ask one question before conceptual or architectural commitment: + +> Am I deciding **what relation/boundary/transformation should exist or matter**, or merely implementing one already established? + +Consult METAPAT for the first case. Continue locally for the second. + +Strong consultation triggers: + +- choosing or revising an architecture-level distinction; +- deciding whether a boundary deserves independent status; +- comparing similarly shaped transformations across different domains; +- importing a domain term, metaphor, formula, or ontology into another layer; +- deciding what remains invariant across scale or representation change; +- a design choice is being mistaken for an empirical or mathematical claim, or vice versa; +- an unexplained but productive discovery path is at risk of being removed only because its mechanism is not yet known; +- two repos disagree because they encode different conceptions of the same relation rather than because of an implementation bug. + +Non-triggers: + +- routine refactors under fixed contracts; +- dependency/version updates; +- deterministic data ingestion; +- tests whose expected relation is already declared; +- formatting, documentation, packaging, CI, deployment, or syntax repair; +- independent recovery of a result after the discovery result and comparison criterion are already frozen. + +When consultation triggers, inspect the current METAPAT repository state before deciding. At minimum resolve the relevant current axioms, postulates, domain-restraint rules, and any directly applicable theory/implementation boundary. Do not import historical skill-lib `meta` wording as authority over current METAPAT. + ## Workflow 1. **Trigger detection**: Activate on any The-Interdependency context or the example trigger phrases listed in the description. -2. **Context assembly**: For transcript work, explicitly structure output using EDCMBONE energy-dissonance mapping, F-metrics, failure-mode tags, and accessibility annotations. Preserve full original relations. -3. **Artifact production**: Write code/docs with msdmd blocks (if applicable) + dedicated "Usage Guidance" section or equivalent. Include examples that can be copy-pasted. -4. **GitHub hygiene**: Check drift, update indexes, propagate only after validation. Reference this skill in commit messages where relevant. -5. **Output packaging**: Structure responses with: +2. **METAPAT gate**: Before conceptual or architectural commitment, run the consultation test above. If triggered, inspect current METAPAT before selecting the relation, boundary, transformation, or cross-domain mapping. +3. **Context assembly**: For transcript work, explicitly structure output using EDCMBONE energy-dissonance mapping, F-metrics, failure-mode tags, and accessibility annotations. Preserve full original relations. +4. **Artifact production**: Write code/docs with msdmd blocks (if applicable) + dedicated "Usage Guidance" section or equivalent. Include examples that can be copy-pasted. +5. **GitHub hygiene**: Check drift, update indexes, propagate only after validation. Reference this skill in commit messages where relevant. +6. **Output packaging**: Structure responses with: - Preserved structure / epistemic layers first. - EDCMBONE-mapped analysis where transcripts are involved. - Usage guidance and examples. @@ -54,6 +86,9 @@ description: Protocol and workflow for all tasks involving The Interdependency o - Canonizing inferred patterns without source backing (pair with `canon` skill). - Omitting `hmmm` when uncertainty or missing source exists. - Treating repo-local copies as canonical source of truth. +- Using METAPAT to decorate a routine implementation decision. +- Making a conceptual architecture choice that crosses the METAPAT gate without consulting current METAPAT. +- Copying METAPAT doctrine into skill-lib and allowing the copy to become a competing authority. ## Output Rubric (active whenever this skill is loaded) @@ -61,10 +96,12 @@ description: Protocol and workflow for all tasks involving The Interdependency o - Transcript tasks → EDCMBONE-structured output (energy maps, F1–F6 tags, accessibility notes, full topology). - Code / docs → msdmd blocks where fitting + prominent, copy-pasteable "Usage Guidance" with examples and integration notes. - GitHub / research → Drift status noted, index updates performed, relevant skills cross-referenced. +- If the METAPAT gate triggered, state what conceptual boundary required consultation and preserve any remaining `hmmm`. - Always close with actionable next steps and any open `hmmm` items. hmmm -- Precise auto-detection triggers or harness integration for automatic loading of this skill (currently relies on description match in agent harness). +- Precise harness integration for automatically fetching current METAPAT after this gate triggers; the skill currently defines the decision rule and source-of-truth boundary, while the consuming agent uses its available GitHub/local-repo access. +- Whether the historical `meta` skill should remain as a compatibility router or be removed after all consumers propagate this gate. - Whether a companion metadata-block skill (e.g. `# === TIW_WORKFLOW ===` or `# === INTERDEPENDENCY ===`) should be added for self-declaring modules inside The-Interdependency repos. - Deeper integration with a0p-instancing / agent-instantiation so that TIW-context automatically loads this skill for sub-agents. - Exact canonical reference for the full EDCMBONE transcript assembly protocol — should the detailed steps live in this skill or be expanded inside the edcmbone repo's own skill definitions? diff --git a/AGENTS.md b/AGENTS.md index cb358b7..05bf71c 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -24,6 +24,25 @@ Authority and invariants: consume an explicitly injected measurement provider; it must not maintain a shadow EDCM implementation. +## Construction and evaluation boundary + +- Build the selected PTCNA architecture faithfully. Curiosity may select the + object of inquiry; neither upstream validation nor a simpler baseline grants + permission to construct it. +- Build and maintain a dependable simpler fallback behind an explicit interface. + The fallback preserves useful operation if PTCNA fails; it must not silently + replace, redefine, or be reported as PTCNA. +- "Does it work?" is the critical falsifiability question. Freeze the + representative workload, comparator, exact metrics and aggregation, + thresholds, resource bounds, stopping rules, and failure propagation before + inspecting outcomes. This freeze governs the verdict, not construction. +- Build PTCNA-local prime and ring structures under local provenance. Claiming + those structures are UCNS-produced remains suspended until an exact pinned + UCNS receipt exists. +- Record terminal status before repair: `FALSIFIED`, `SURVIVED — not proved`, + or `UNRESOLVED`. A simpler recovery method may supply the fallback; it does + not invalidate the architecture that selected the discovery path. + Before changing code, load the applicable repo-local skills under `.agents/skills/`. All new or materially revised modules need self-declared `MODULE_BUILD`, `CONTRACTS`, and actual runtime `BOUNDARIES` metadata when the diff --git a/docs/architecture.md b/docs/architecture.md index 013aa88..4f88efa 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -70,11 +70,38 @@ descriptive layer expansions. 7. Rewire interdependent-lib (`ptcna` key/extra; rewrite stack canon). 8. Archive `pcna`, `pcta`, `pcsa`. -## Blockers for me - -- **Confirm I should create `The-Interdependency/ptcna`** (outward action). -- **Add `pcsa` to session scope** — I need the core-layer source to migrate it. - (`pcna`, `pcta` already cloned.) +## Construction and falsifiability contract + +Construction of the selected PTCNA architecture is active. It is not conditional +on upstream validation, baseline superiority, or prior explanation of why its +structure may work. + +Two implementation paths are required: + +1. Build the intended PTCNA architecture faithfully under PTCNA-local + provenance. +2. Build and independently verify a dependable simpler fallback behind an + explicit interface. + +The fallback preserves useful operation if PTCNA fails. It does not replace, +redefine, or grant permission to construct PTCNA. + +The critical falsifiability question is: **Does it work?** Freeze the +representative workload, comparator, exact metrics and aggregation, thresholds, +resource bounds, stopping rules, and failure propagation before inspecting +outcomes. That preregistration governs the verdict, not whether construction may +begin. + +Record `FALSIFIED`, `SURVIVED — not proved`, or `UNRESOLVED` before repair +or criterion change. PTCNA-local prime and ring structures may be constructed +now; only a claim that they are UCNS-produced remains suspended until an exact +pinned UCNS receipt exists. + +Semantic authority for discovery-before-recovery remains with +`The-Interdependency/metapat`; this correction consulted +`metapat@53315e30c54aba881a5b48cbf395890e83ab05c5`, +`POSTULATES.md`, Seventh Postulate. The reference is provenance, not copied +METAPAT canon. ## Status log diff --git a/docs/work-graphs/repository-plan-report.json b/docs/work-graphs/repository-plan-report.json index 8a5def1..a12a7e9 100644 --- a/docs/work-graphs/repository-plan-report.json +++ b/docs/work-graphs/repository-plan-report.json @@ -11,15 +11,16 @@ "source": { "branch": "main", "commit": "4509d33419aa25e6a9cfef415055e378b8f37edc", - "generated_at": "2026-08-15", - "note": "This report describes the executable PTCNA 0.1.1 runtime at the cited main commit plus the current repo-owned plan. Operational-shell and report-only maintenance do not upgrade runtime, mathematical, measurement, or architectural evidence standing." + "generated_at": "2026-08-17", + "note": "This report describes the executable PTCNA 0.1.1 runtime at the cited main commit plus the current repo-owned plan. The 2026-08-17 policy correction removes an unauthorized evaluation-as-permission gate: intended architecture construction, dependable fallback construction, and evaluation are distinct work streams. Operational-shell and report-only maintenance do not upgrade runtime, mathematical, measurement, or architectural evidence standing." }, "authority": { "owns": [ "PTCNA neural, circle, seed, and core runtime definitions and implementation", "PTCNA neural-only reverse-mode differentiation and structural host boundaries", "PTCNA local composition, checkpoint, propagation, timing, and audit behavior", - "PTCNA producer-side integration boundaries and runtime evidence" + "PTCNA producer-side integration boundaries and runtime evidence", + "PTCNA-local selection and faithful construction of the experimental architecture and its explicit dependable-fallback boundary" ], "does_not_own": [ "UCNS mathematical representation canon, higher-gonol producer profiles, or proof status", @@ -33,7 +34,8 @@ "UCNS proof or representation status does not establish PTCNA learning efficacy", "EDCM measurement results do not become PTCNA-owned evidence merely because a caller injects them", "a functioning four-layer implementation does not establish that prime structure, current ring constants, or current weight topology are necessary or superior", - "suspended integration remains suspended until an exact producer contract is independently available and reviewed" + "suspended integration remains suspended until an exact producer contract is independently available and reviewed", + "upstream evidence and simpler-baseline performance inform attribution, evaluation, and fallback routing; they neither grant nor deny permission to construct the selected PTCNA architecture" ] }, "portfolio_role": { @@ -47,8 +49,8 @@ } }, "status": { - "state": "active alpha runtime; architecture modernization suspended on upstream falsification", - "current_claim": "PTCNA 0.1.1 implements one four-layer runtime in which reverse-mode gradients are owned by the neural layer while circle, seed, and core remain non-differentiating structural hosts. UCNS higher-gonol integration is explicitly suspended, EDCM remains external, and no claim is established that the current prime/ring topology or learned weight path is necessary, superior, or the final architecture.", + "state": "active alpha runtime; intended architecture and dependable fallback construction proceed under separate evidence boundaries", + "current_claim": "PTCNA 0.1.1 implements one four-layer runtime in which reverse-mode gradients are owned by the neural layer while circle, seed, and core remain non-differentiating structural hosts. Construction of the intended PTCNA architecture may proceed under PTCNA-local provenance alongside a dependable explicit fallback. UCNS higher-gonol attribution remains suspended, EDCM remains external, and the critical 'does it work?' verdict remains unearned until frozen evaluation.", "latest_main_milestone": { "commit": "4509d33419aa25e6a9cfef415055e378b8f37edc", "description": "merged the reconciled four-layer v0.1.1 runtime with one CircleTensor, neural-only reverse-mode scalar ownership, fail-closed UCNS integration, and external EDCM measurement injection" @@ -83,44 +85,49 @@ ], "active_frontier": [ "keep the operational shell aligned with current skill-lib doctrine and supported GitHub Actions runtimes without changing PTCNA architectural evidence standing", - "leave UCNS higher-gonol integration suspended while the UCNS-EDCM architectural reconstruction claim is under preregistered falsification", - "if the upstream reconstruction architecture survives, freeze a PTCNA experiment that compares UCNS-derived relational initialization or assignment against the current learned/hash-projected path and simpler matched baselines before replacing runtime architecture", - "if the upstream reconstruction architecture is falsified, deprecate dependent UCNS-specific PTCNA integration assumptions rather than repairing them inside PTCNA", + "construct the intended PTCNA architecture faithfully under PTCNA-local provenance without waiting for upstream validation or a simpler baseline to grant permission", + "build and independently verify a dependable simpler fallback behind an explicit interface so useful operation survives a PTCNA failure without silently replacing or redefining PTCNA", + "freeze the critical 'does it work?' evaluation before outcome inspection, including representative workload, comparator, exact metric and aggregation, threshold, resource bounds, stopping rules, failure propagation, and evidence receipt", + "consume exact UCNS producer receipts when available for UCNS attribution while allowing locally attributed PTCNA prime and ring construction to continue", "resolve whether the embedded ZetaEngine remains a bounded PTCNA-local measurement-to-learning adapter or should be removed in favor of separate ZFAE authority before further Zeta development", - "test sustained-load and long-horizon state behavior only after the architecture under test and its authority boundaries are frozen" + "test sustained-load and long-horizon state behavior after the architecture and fallback are executable and the evaluation contract is frozen" ], "next_actions": [ { - "action": "maintain the current four-layer runtime and fail-closed UCNS boundary while the UCNS-EDCM run-to-completion resolves the load-bearing reconstruction claim", + "action": "build the intended PTCNA architecture faithfully under PTCNA-local provenance", "owner": "The-Interdependency/ptcna", - "dependency": "do not introduce a PTCNA-specific UCNS producer profile or redesign weight topology before upstream architectural evidence is resolved" + "dependency": "repository-owned implementation contracts only; upstream evidence and simpler baselines do not grant permission to construct" }, { - "action": "on upstream survival, preregister the smallest decisive PTCNA architecture test comparing UCNS-derived relational initialization or assignment with the current implementation and simpler matched-information baselines", + "action": "build and independently verify a dependable simpler fallback behind the same explicit task boundary", "owner": "The-Interdependency/ptcna", - "dependency": "requires exact surviving UCNS identities, frozen construction rules, explicit EDCM measurement authority, and outcome criteria fixed before execution" + "dependency": "the fallback must remain separately identified and must not silently replace, redefine, or be reported as PTCNA" }, { - "action": "on upstream falsification, record and remove dependent UCNS-specific PTCNA architecture assumptions before further implementation", + "action": "preregister the critical 'does it work?' evaluation after the target and fallback are sufficiently executable and before outcome inspection", "owner": "The-Interdependency/ptcna", - "dependency": "triggered only by a falsified load-bearing upstream claim with propagated downstream effect" + "dependency": "freeze workload, comparator, metric and aggregation, threshold, resource bounds, stopping rules, failure propagation, and evidence-receipt requirements" + }, + { + "action": "record the terminal result before repair or criterion change", + "owner": "The-Interdependency/ptcna", + "dependency": "FALSIFIED routes useful operation to the fallback; SURVIVED — not proved preserves the architecture for the next bounded test; UNRESOLVED repairs only the failed prerequisite" }, { "action": "freeze the authority decision for the embedded ZetaEngine before modifying its learning role", "owner": "The-Interdependency/ptcna", - "dependency": "requires comparison with the current ZFAE repository contract; unresolved authority must remain hmmm" + "dependency": "requires comparison with the current ZFAE repository contract; unresolved authority remains hmmm" } ], "blocked": [ - "activation of UCNS higher-gonol composition is blocked on an exact reviewed PTCNA-specific UCNS producer profile and on survival of the load-bearing upstream reconstruction architecture", - "replacement of current learned/hash-projected neural topology with UCNS-derived relational initialization is blocked until a preregistered comparison can be interpreted against simpler baselines", - "further architectural expansion is blocked from treating current prime constants, ring sizes, heptagram propagation, or hard-coded ring weights as established necessities", + "claiming that PTCNA-local prime or ring construction is UCNS-produced is blocked until an exact reviewed PTCNA-specific UCNS producer receipt exists", + "claiming that PTCNA works, learns usefully, or is necessary or superior is blocked until the frozen evaluation earns that standing", "ZetaEngine ownership migration or expansion is blocked until the PTCNA-local versus separate-ZFAE authority boundary is frozen" ], "cross_repository_relations": [ { "repository": "The-Interdependency/ucns", - "relation": "mathematical and relational producer candidate; PTCNA integration remains suspended until an exact reviewed producer profile and surviving architectural evidence exist", + "relation": "mathematical and relational producer authority; exact UCNS attribution requires a reviewed producer receipt, while PTCNA-local construction proceeds under local provenance", "authority_transfer": false, "proof_status_transfer": false }, @@ -130,6 +137,11 @@ "authority_transfer": false, "measurement_status_transfer": false }, + { + "repository": "The-Interdependency/metapat", + "relation": "semantic authority for discovery-before-recovery and the distinction between constructing an inquiry target and independently evaluating its result", + "authority_transfer": false + }, { "repository": "The-Interdependency/skill-lib", "relation": "canonical build, evidence, skill propagation, and cross-repository coordination doctrine", @@ -157,12 +169,13 @@ "quality_workflow": ".github/workflows/quality.yml" }, "hmmm": [ - "whether the UCNS-EDCM prime-view reconstruction architecture survives its run-to-completion adversarial program", - "the exact PTCNA-specific UCNS producer profile, if one remains justified after that program", - "whether UCNS-derived relational initialization or assignment outperforms the current implementation and simpler matched baselines", + "the exact PTCNA-specific UCNS producer profile and receipt for any structure later claimed as UCNS-produced", + "whether the constructed PTCNA architecture works under the frozen representative evaluation", + "the exact workload, comparator, metric, aggregation, threshold, resource bounds, stopping rules, and failure propagation for that evaluation", + "the exact dependable fallback implementation and shared task-interface identity", "whether the current ring sizes, heptagram propagation, prime constants, and fixed ring weights contain irreducible useful structure or historical accident", "the authority boundary and migration path between PTCNA's embedded ZetaEngine and The-Interdependency/zfae", "sustained-load behavior across the complete four-layer seam", - "PyPI 0.1.1 publication artifact identity; the GitHub repository currently exposes no release record" + "the Git commit provenance of the published PyPI 0.1.1 artifacts; the GitHub repository currently exposes no release or tag binding" ] }