project-tiny-context-harness 0.7.8 → 0.8.0

package/assets/skills/long-task-workflow/references/evidence-design.md

@@ -1,75 +1,78 @@
-# Evidence Design Reference
-
-Read this only while designing or repairing Contract Checks and proof.
-
-## General Proof Rules
-
-- Every Outcome has at least one executable Check and one non-Result atomic Claim.
-- Required proof surfaces are non-empty, unique and all-of. Claim-bearing Assertions use explicit comparable Observations and expected values.
-- `truthy`/`falsy` are diagnostic-only. `exists` proves only implementation-structure obligations. Missing or type-incomparable Observation never proves a Claim; negative proof uses an explicit value such as `equals: false`.
-- Claim and Population proof is emitted only after the entire Check passes. Exit failure, missing artifact, failed population, failed Assertion or invalid Counterfactual yields no Claim proof.
-- Verification inputs include entrypoints, helpers, fixtures/config, package scripts and lockfiles and cannot overlap implementation carriers.
-- Runners receive the minimum environment whitelist plus only declared environment requirements. Never expose actual secret values in findings.
-
-## Runner And Observation Identity
-
-Evidence adapter is derived from runner kind. Only Playwright may prove `ui_browser`; structured runners prove non-browser surfaces. Raw Execution identity binds frozen runner identity and canonical declared Environment Requirements, not actual values.
-
-Across all Checks sharing a Raw Execution, one Claim-bearing Observation belongs to one Assertion. Shared setup may execute once only when independent per-Check observations and artifacts remain unambiguous.
-
-## Scenario And Evidence Capabilities
-
-- Every Check declares non-empty keyed `scenario.given` and `scenario.when` steps. One Check covers one materially coherent journey; a different success path belongs in another Check or vertical Outcome.
-- Every Assertion declares a non-empty all-of `evidence_capabilities` set. `presence` proves static existence only and cannot alone prove a behavioral Claim. Each other capability requires exactly one typed current-execution record bound to the declared Assertion key; missing, duplicate, unknown or undeclared records fail closed.
-- `interaction_trace` names the exact target plus the declared Given keys and ordered action keys. Playwright derives it only from an executed declared AC carrying matching `[given:<key>]` and `[action:<key>]` steps; `[ac:<assertion-key>]` remains the AC binding.
-- `state_delta` requires different before/after hashes and named changed fields. `durable_readback` requires independent write/read sessions with equal state hashes. `cross_surface_consistency` requires at least two distinct surface refs, known target refs and one state hash.
-- `boundary_invocation` and `external_side_effect` require the Check itself to execute on the named observer target. `failure_injection` requires an observed fault and recovery state; `visual_render` binds a declared artifact hash; `target_runtime` binds exact target/root/current session and requires a cold start for a root journey; `input_variation` requires at least two distinct inputs, differing propagated outputs and an observed failure case.
-- Structured runners emit `long-task-check-result-v3` for capability records. V2 payloads remain decodable only for presence-only compatibility; they cannot satisfy a declared non-presence capability. Evidence records contain bounded hashes/ids/refs, not unrestricted raw payloads.
-
-## Live Target Runtime Evidence
-
-- For a target-runtime Claim, the accepting Check must exercise the exact declared required target during the current runner invocation and derive structured Observations from the same runtime session. Browser target runtime is proved only by Playwright; Native/Desktop target runtime is proved only by the project binary. Rerunning a parser for a tracked or generated status report reruns the parser, not the target.
-- A proxy surface may prove its own Claim but cannot substitute when proxy and target can fail independently. Static source/config shape proves structure only. The existence of a build, installation, started process or clean fatal-error scan proves only those exact assertions.
-- If the declared result includes a runnable product surface or interaction, observe a stable product-owned sentinel or the declared interaction in the target session. A generic process/activity/window, development shell or absence of errors is insufficient for that broader Claim.
-- Historical reports, screenshots, binaries and logs are review material. Current-run screenshots/logs may accompany a Check as Artifacts, but the accepting Observation must come from the live runner execution and cannot be imported from historical state.
-- Bind every runtime-affecting implementation surface through `input_paths` and relevant Binding carriers; keep runner/helper/config files in `verification_inputs`. This lets existing Progress freshness identify when rolling feedback is stale without a new trigger registry.
-
-## Causal Boundary Review After Revision
-
-- When a rolling blocker causes a semantic or proof revision, review only the affected weak-observability or high-risk Outcomes before adoption. Ask whether a cheaper proxy, fixed response or self-reported success could pass while the declared result still fails at a farther independent boundary.
-- Evidence must reach the furthest independently failing boundary named by the Claim. A proxy may prove its own result, but it cannot prove a downstream state or effect merely by reporting success.
-- For a behavioral Claim, prefer a Counterfactual that disrupts the claimed causal capability when removing a carrier would prove only file dependence. `replace_file` may supply a declared inert/failing implementation fixture; `remove_paths` remains valid when carrier existence is itself the claimed boundary.
-- Keep this risk-proportional and internal. Do not create an evidence matrix, product-effect taxonomy, universal restart/end-to-end suite, new mutation type or persistent review state.
-
-For semantic Product Conformance, require one separate read-only Global `conformance` Check only when `weak_observability` combines with multiple Stages or multiple required product runtime families. It starts from a required root product target, includes `target_runtime`, uses a Raw Execution identity independent of Outcome Checks and runs inside the existing Final Gate. Single-Stage/single-family weak work keeps the existing same-Check sensitivity path and does not pay this extra runtime cost.
-
-## Playwright
-
-Claim-bearing Playwright proof is only `playwright.case.<ac-key>.passed equals true`. `[ac:<assertion-key>]` binds one declared AC per Test Instance; ordinary tags are ignored and legacy `[<key>]` binds only a declared key.
-
-Missing, skipped, flaky, unexpected, timed-out, interrupted, failed, multi-AC and duplicate-within-project cases fail closed. The same AC across distinct projects aggregates all-of. Aggregate status/count fields are diagnostic-only.
-
-Standard frozen Playwright verifier content is trusted. Weak-observability Outcomes require same-Check AC/Claim sensitivity. A weak Playwright Counterfactual may accept exit one only when every unexpected instance is uniquely a designated executed AC failure and there are no root, unbound, extra, missing, skipped, flaky, timeout, interruption, artifact, population, environment or other evidence failures. Ordinary Baseline Checks require exit zero.
-
-## Visual UI Evidence
-
-- When external design resources are Source, prove only selected exact-target/constraint conditions that the Contract explicitly adopts. Candidate comparison, a Figma link or an isolated prototype run is authoring/review material and cannot become product acceptance. Resolve each acceptance-affecting resource through a stable locator plus immutable path/version/hash and declared condition coverage before Compile.
-- Use Playwright for every declared `ui_browser` visual AC and bind each independently falsifiable AC to its own `[ac:<assertion-key>]` Test Instance. A broad screenshot or one passing page case does not silently prove separate viewport, theme, state, content-stress, layout or accessibility claims.
-- Make the test environment deterministic enough for its claim: freeze the relevant browser/project, viewport, theme/mode, locale/timezone, font loading, fixtures/data and animation/motion policy in declared verifier inputs or configuration.
-- Any reviewed screenshot baseline that affects pass/fail must exist for the accepting Compile and be included in `verification_inputs`. Generated screenshots, diffs and reports are Artifacts and review material; they are not editable acceptance authority. Creating or replacing a baseline after Authority Lock is verifier-material revision and must never be silently auto-updated to make a failure pass.
-- Confirm that each baseline is a selected `exact-target` for the named surface/viewport/theme/state or implements a named `constraint`; an inspiration reference cannot become a fidelity oracle merely because it is available. The implementation's current screenshot is never its own target.
-- Screenshot comparison proves only the named visual similarity claim. Pair it with explicit DOM/layout/accessibility assertions when the Contract separately claims no overflow, action visibility, focus behavior, target size, semantic state, reduced motion or other observable behavior.
-- Keep evidence aligned with stable surface/control/target keys. Visual similarity, interaction/navigation, validation/recovery, permission behavior, accessibility and target-runtime conformance are independently failing claims and need their own Assertions/capabilities when declared; one broad screenshot or UI pass cannot prove all Control fields.
-- Run checks against production components or real product routes. A detached kit/mock harness is acceptable only when the Contract explicitly makes that artifact the product surface; otherwise it cannot substitute for the production carrier.
-- Keep subjective visual quality and approval external. A new visual direction or baseline that needs human judgment remains an explicit external confirmation even when all machine checks pass.
-- `ui_browser` proves browser UI only. When a native/mobile/desktop UI can fail independently, browser output is proxy evidence; require a project-owned live target-runtime Check that truthfully fits an existing proof surface or keep the device/simulator review external.
-
-## Structured Evidence And Sensitivity
-
-Every claim-bearing `structured_json_v2` Check needs same-Check Claim-related Counterfactual sensitivity unless the Claim is covered by that same Check's Population proof; weak observability removes that Population exemption. Artifacts and another Check never substitute for sensitivity.
-
-Outcome Counterfactual V2 names an Outcome `binding_key`; Global Counterfactual V2 resolves an Outcome-owned `binding_ref`. A Counterfactual mutates only a proven subset of implementation carriers, never Source, Context, runners or verification inputs, and accepts only designated `assertion_value_mismatch` findings.
-
-An `existing` mutation target must exist at Preflight/Compile. A `planned` target may be absent until implementation but must exist at Final Gate; once created, its changes stale targeted Progress. Population V2 proves exact eligible = observed + valid exclusions by entity id.
-
-Artifacts remain review material. They do not prove Claim sensitivity by themselves.
+# Evidence Design Reference
+
+Read this only while designing or repairing Contract Checks and proof.
+
+## General Proof Rules
+
+- Every Outcome has at least one executable Check and one non-Result atomic Claim.
+- Required proof surfaces are non-empty, unique and all-of. Claim-bearing Assertions use explicit comparable Observations and expected values.
+- `truthy`/`falsy` are diagnostic-only. `exists` proves only implementation-structure obligations. Missing or type-incomparable Observation never proves a Claim; negative proof uses an explicit value such as `equals: false`.
+- Claim and Population proof is emitted only after the entire Check passes. Exit failure, missing artifact, failed population, failed Assertion or invalid Counterfactual yields no Claim proof.
+- Verification inputs include entrypoints, helpers, fixtures/config, package scripts and lockfiles and cannot overlap implementation carriers.
+- Runners receive the minimum environment whitelist plus only declared environment requirements. Never expose actual secret values in findings.
+
+## Runner And Observation Identity
+
+Evidence adapter is derived from runner kind. Only Playwright may prove `ui_browser`; structured runners prove non-browser surfaces. Raw Execution identity binds frozen runner identity and canonical declared Environment Requirements, not actual values.
+
+Across all Checks sharing a Raw Execution, one Claim-bearing Observation belongs to one Assertion. Shared setup may execute once only when independent per-Check observations and artifacts remain unambiguous.
+
+## Scenario And Evidence Capabilities
+
+- Every Check declares non-empty keyed `scenario.given` and `scenario.when` steps. One Check covers one materially coherent journey; a different success path belongs in another Check or vertical Outcome.
+- Every Assertion declares a non-empty all-of `evidence_capabilities` set. `presence` proves static existence only and cannot alone prove a behavioral Claim. Each other capability requires exactly one typed current-execution record bound to the declared Assertion key; missing, duplicate, unknown or undeclared records fail closed.
+- `interaction_trace` names the exact target plus the declared Given keys and ordered action keys. Playwright derives it only from an executed declared AC carrying matching `[given:<key>]` and `[action:<key>]` steps; `[ac:<assertion-key>]` remains the AC binding.
+- `state_delta` requires different before/after hashes and named changed fields. `durable_readback` requires independent write/read sessions with equal state hashes. `cross_surface_consistency` requires at least two distinct surface refs, known target refs and one state hash.
+- `boundary_invocation` and `external_side_effect` require the Check itself to execute on the named observer target. `failure_injection` requires an observed fault and recovery state; `visual_render` binds a declared artifact hash; `design_conformance` binds one compiled selected target, exact required product target, declared condition set and distinct current actual/comparison artifact paths; `target_runtime` binds exact target/root/current session and requires a cold start for a root journey; `input_variation` requires at least two distinct inputs, differing propagated outputs and an observed failure case.
+- Structured runners emit `long-task-check-result-v3` for capability records. V2 payloads remain decodable only for presence-only compatibility; they cannot satisfy a declared non-presence capability. Evidence records contain bounded hashes/ids/refs, not unrestricted raw payloads.
+
+## Live Target Runtime Evidence
+
+- For a target-runtime Claim, the accepting Check must exercise the exact declared required target during the current runner invocation and derive structured Observations from the same runtime session. Browser target runtime is proved only by Playwright; Native/Desktop target runtime is proved only by the project binary. Rerunning a parser for a tracked or generated status report reruns the parser, not the target.
+- A proxy surface may prove its own Claim but cannot substitute when proxy and target can fail independently. Static source/config shape proves structure only. The existence of a build, installation, started process or clean fatal-error scan proves only those exact assertions.
+- If the declared result includes a runnable product surface or interaction, observe a stable product-owned sentinel or the declared interaction in the target session. A generic process/activity/window, development shell or absence of errors is insufficient for that broader Claim.
+- Historical reports, screenshots, binaries and logs are review material. Current-run screenshots/logs may accompany a Check as Artifacts, but the accepting Observation must come from the live runner execution and cannot be imported from historical state.
+- Bind every runtime-affecting implementation surface through `input_paths` and relevant Binding carriers; keep runner/helper/config files in `verification_inputs`. This lets existing Progress freshness identify when rolling feedback is stale without a new trigger registry.
+
+## Causal Boundary Review After Revision
+
+- When a rolling blocker causes a semantic or proof revision, review only the affected weak-observability or high-risk Outcomes before adoption. Ask whether a cheaper proxy, fixed response or self-reported success could pass while the declared result still fails at a farther independent boundary.
+- Evidence must reach the furthest independently failing boundary named by the Claim. A proxy may prove its own result, but it cannot prove a downstream state or effect merely by reporting success.
+- For a behavioral Claim, prefer a Counterfactual that disrupts the claimed causal capability when removing a carrier would prove only file dependence. `replace_file` may supply a declared inert/failing implementation fixture; `remove_paths` remains valid when carrier existence is itself the claimed boundary.
+- Keep this risk-proportional and internal. Do not create an evidence matrix, product-effect taxonomy, universal restart/end-to-end suite, new mutation type or persistent review state.
+
+For semantic Product Conformance, require one separate read-only Global `conformance` Check only when `weak_observability` combines with multiple Stages or multiple required product runtime families. It starts from a required root product target, includes `target_runtime`, uses a Raw Execution identity independent of Outcome Checks and runs inside the existing Final Gate. Single-Stage/single-family weak work keeps the existing same-Check sensitivity path and does not pay this extra runtime cost.
+
+## Playwright
+
+Claim-bearing Playwright proof is only `playwright.case.<ac-key>.passed equals true`. `[ac:<assertion-key>]` binds one declared AC per Test Instance; ordinary tags are ignored and legacy `[<key>]` binds only a declared key.
+
+Missing, skipped, flaky, unexpected, timed-out, interrupted, failed, multi-AC and duplicate-within-project cases fail closed. The same AC across distinct projects aggregates all-of. Aggregate status/count fields are diagnostic-only.
+
+Standard frozen Playwright verifier content is trusted. Weak-observability Outcomes require same-Check AC/Claim sensitivity. A weak Playwright Counterfactual may accept exit one only when every unexpected instance is uniquely a designated executed AC failure and there are no root, unbound, extra, missing, skipped, flaky, timeout, interruption, artifact, population, environment or other evidence failures. Ordinary Baseline Checks require exit zero.
+
+## Visual UI Evidence
+
+- A selected implementation handoff must already pass `ty-context design-resource preflight`. For each covered row, turn its declared verification methods into project-owned, independently failing observations in the target conformance Check: geometry/pixel/token/content, component state/interaction trace, motion timeline, responsive reflow/input method, accessibility semantics and asset integrity are different obligations. The strict index proves that none was silently omitted; it does not prove that the project verifier implemented or passed them.
+- Keep `design_resource_integrity` and `design_implementation_conformance` distinct. Stable paths/hashes, provider/export success, manifest/registry membership and expected counts prove resource integrity; `visual_render` proves a current artifact exists. Neither proves the production implementation matches a selected target.
+- When external design resources are Source, prove only selected exact-target/constraint conditions that the Contract explicitly adopts. Candidate comparison, a mutable provider link, extraction success, metadata-only output, resource digest or an isolated prototype run is authoring/integrity material and cannot become product acceptance. Resolve each acceptance-affecting fact through a typed locator plus immutable path/hash and declared target/condition applicability before Compile. Include the handoff and every source-profile entry/dependency in `verification_inputs`; project-owned method-specific design-conformance, interaction and target-runtime observations must still fail independently on the current production target.
+- A `design_conformance` record is accepted only for the compiled target/Assertion/current Check target, an equal declared condition-key set and both declared actual/comparison artifacts collected by the current Check. Missing or swapped targets, conditions or artifacts fail closed; the implementation render cannot also be the comparison authority.
+- Use Playwright for every declared `ui_browser` visual AC and bind each independently falsifiable AC to its own `[ac:<assertion-key>]` Test Instance. A broad screenshot or one passing page case does not silently prove separate viewport, theme, state, content-stress, layout or accessibility claims.
+- Make the test environment deterministic enough for its claim: freeze the relevant browser/project, viewport, theme/mode, locale/timezone, font loading, fixtures/data and animation/motion policy in declared verifier inputs or configuration.
+- Any reviewed screenshot baseline that affects pass/fail must exist for the accepting Compile and be included in `verification_inputs`. Generated screenshots, diffs and reports are Artifacts and review material; they are not editable acceptance authority. Creating or replacing a baseline after Authority Lock is verifier-material revision and must never be silently auto-updated to make a failure pass.
+- Confirm that each baseline is a selected `exact-target` for the named surface/viewport/theme/state or implements a named `constraint`; an inspiration reference cannot become a fidelity oracle merely because it is available. The implementation's current screenshot is never its own target.
+- Screenshot comparison proves only the named visual similarity claim. Pair it with explicit DOM/layout/accessibility/motion/responsive/input assertions whenever the handoff or Contract separately declares no overflow, action visibility, focus behavior, target size, semantic state, reduced motion or other observable behavior. One generic `design_conformance` record cannot erase distinct Source Claims or verification methods; every handoff method binds a separate Assertion and the trusted Check must fail if any asserted method fails.
+- Keep evidence aligned with stable surface/control/target keys. Visual similarity, interaction/navigation, validation/recovery, permission behavior, accessibility and target-runtime conformance are independently failing claims and need their own Assertions/capabilities when declared; one broad screenshot or UI pass cannot prove all Control fields.
+- Run checks against production components or real product routes. For each bound Control, the named root-entry journey must begin at the required product target root, execute the declared entry action and prove its navigation result—or interaction, trigger or location fallback—with `interaction_trace` plus `target_runtime`. A detached kit/mock/deep-link harness is acceptable only when the Contract explicitly makes that artifact the product surface; otherwise it cannot substitute for the production carrier or root journey.
+- Keep subjective visual quality and approval external. A new visual direction or baseline that needs human judgment remains an explicit external confirmation even when all machine checks pass.
+- `ui_browser` proves browser UI only. When a native/mobile/desktop UI can fail independently, browser output is proxy evidence; require a project-owned live target-runtime Check that truthfully fits an existing proof surface or keep the device/simulator review external.
+
+## Structured Evidence And Sensitivity
+
+Every claim-bearing `structured_json_v2` Check needs same-Check Claim-related Counterfactual sensitivity unless the Claim is covered by that same Check's Population proof; weak observability removes that Population exemption. Artifacts and another Check never substitute for sensitivity.
+
+Outcome Counterfactual V2 names an Outcome `binding_key`; Global Counterfactual V2 resolves an Outcome-owned `binding_ref`. A Counterfactual mutates only a proven subset of implementation carriers, never Source, Context, runners or verification inputs, and accepts only designated `assertion_value_mismatch` findings.
+
+An `existing` mutation target must exist at Preflight/Compile. A `planned` target may be absent until implementation but must exist at Final Gate; once created, its changes stale targeted Progress. Population V2 proves exact eligible = observed + valid exclusions by entity id.
+
+Artifacts remain review material. They do not prove Claim sensitivity by themselves.

package/assets/skills/long-task-workflow/references/source-authoring.md

@@ -1,98 +1,101 @@
-# Integrated Source Authoring Reference
-
-Read this when raw, mixed, attachment-heavy or incomplete inputs need to become self-contained delivery Source before Contract mapping. This work occurs inside the same `long-task-workflow` Goal and feeds the same Contract Draft; it is not a standalone Source Plan stage or second lifecycle.
-
-## Objective and boundary
-
-Preserve every material user, product, technical, visual and acceptance constraint from the initial/revised proposal and supplied resources. Add only traceable necessary derivations, defensible delegated choices and evidence-backed repository facts. Make the real Source understandable without the original conversation.
-
-Do not create a Source Plan schema, CLI, Preflight, Compile, Receipt, cache, authority or state. Do not bind a choice only in Contract YAML. Do not let current implementation silently redefine intent. A pre-existing Source Plan is simply one possible input.
-
-## Input inventory
-
-1. Assign every proposal, selected design resource, screenshot, document, diagram, table and other attachment a stable input ID.
-2. Inspect all material pages/frames/screens/tables/visible states; never silently sample a multi-part artifact.
-3. Classify each input as user instruction, product requirement, technical constraint, existing proposal, selected target, repository/Context evidence, constraint, inspiration or background.
-4. For visual resources, preserve selection basis, classification (`exact-target`, `constraint` or `inspiration`), stable resource/surface/control/state/target keys, declared platform/viewport/mode/state/content coverage, provider/project/run/entry provenance and immutable digest/snapshot. Unselected candidates authorize no fidelity.
-5. Record incorporated meaning and every unreadable, conflicting or intentionally unused part. Higher authority and user-stated precedence win; unresolved conflicts remain decisions.
-
-## Preference and research gate
-
-Before comparative research or a material product, technical, architecture or provider selection, identify decision-changing criteria such as fidelity versus cost, delivery speed, reliability/support, privacy/compliance, lock-in/control, operational burden, platform scope and extensibility.
-
-Infer preferences only from user words, Source, Context or controlling constraints. If an unknown preference would materially change research or recommendation, ask one concise targeted clarification before proceeding. Do not impose a questionnaire, re-ask known preferences or pause for minor reversible choices with the same defensible recommendation.
-
-Use current primary/authoritative evidence for changing external facts. Record source, scope and retrieval date. Preference clarification authorizes plan meaning, not payment, contracting, deployment/publication, destructive production mutation, permission grants, sensitive-data transmission or required legal/security/human approval; those remain typed external confirmations.
-
-## Authoring modes
-
-Infer rather than ask the user to choose:
-
-- **refinement:** preserve and complete a substantially developed proposal;
-- **synthesis:** build coherent Source from a goal plus mixed inputs;
-- **hybrid:** use one proposal as backbone and fill gaps from other inputs.
-
-A short request is sufficient when roles, goal and reference authority are recoverable. Reuse an authorized writable proposal as the real Source. If the delivery exists only in conversation, materialize exactly one project-native Markdown Source according to repository convention. Do not create a parallel planning artifact.
-
-## Semantic authoring
-
-For every material item, preserve one origin:
-
-- `direct`: stated by user or controlling input, with all qualifiers;
-- `derived`: unavoidable for completeness/falsifiability, identifies `Derived From`, states why necessary and changes no user capability, business rule or scope;
-- `delegated`: a defensible choice requested by instructions to synthesize/refine/use judgment, records `Delegated By`, preference/evidence basis and exact added meaning;
-- `evidence-backed`: repository/Context fact with exact source and no promotion of incidental code shape to product intent;
-- `decision_required`: conflicting authority, explicitly user-reserved choice, missing material preference or no defensible recommendation.
-
-High impact or several options is not itself a reason to pause when criteria support one recommendation. Keep real high-risk actions as external confirmations. Never introduce a requirement for the first time only inside acceptance criteria.
-
-## Structure and stable keys
-
-Use stable semantic lowercase-kebab keys and Markdown anchors where practical. Preserve keys when wording changes but meaning does not; never renumber for ordering or reuse a retired key for new meaning.
-
-Define vertical Outcomes only when observable results are independently decidable and later verifiable. Do not split by response length, frontend/backend layer, module count, agent capacity or desired parallelism; do not merge distinct results merely for brevity.
-
-Use only applicable semantic types:
-
-- result/Outcome;
-- Requirement (`REQ`);
-- user-visible Control (`CTRL`);
-- technical obligation (`OBL`);
-- explicitly non-completing meaning (`NCOMP`);
-- acceptance scenario (`AC`);
-- global non-goal/constraint and forbidden shortcut;
-- risk with exact Fact, Affected Outcome, Basis and Consequence;
-- external confirmation (`EXT`);
-- genuine decision (`DEC`);
-- advisory implementation hint (`HINT`), which is not a material requirement.
-
-## UI and control completeness
-
-For each in-scope surface, record purpose, entry/exit/navigation, regions/overlays and included Control keys. For every material interactive control, independently preserve applicable:
-
-`surface`, `region`, `control type`, `label/content`, `location`, `user task`, `visibility`, `availability`, `trigger`, `input`, `validation`, `default`, `interaction`, `navigation/result`, `loading`, `empty`, `success`, `failure`, `recovery`, `permission`, `feedback` and `accessibility`.
-
-Do not invent controls for a non-interface delivery. A coarse frame or configured design system does not supply unshown states. Selected design resources and product/technical Source remain parallel: visuals cannot invent business/data/permission/algorithmic rules.
-
-## Acceptance and risk
-
-Each AC has exactly one Given/When/Then scenario, names the REQ/CTRL/OBL/NCOMP meaning it accepts and introduces no undeclared product semantics. Keep representative/sample/framework checks distinct from full-population claims and partial delivery distinct from completion.
-
-Use the Runtime's exact risk Fact names when marking risk. Data migration is `data_migration`; a weakly observable critical path is separate `critical_user_path` and `weak_observability` facts; preserve `multi_repository_change` in Source so Contract compilation can reject unsupported delivery honestly.
-
-## Completeness audit
-
-Before Contract mapping confirm:
-
-1. Every material original statement and qualifier is preserved.
-2. Every supplied input is incorporated or has an explicit unreadable/unused/conflict disposition.
-3. Distinct requirements and independently decidable Outcomes were not collapsed.
-4. Every material UI surface/control/state is explicit or marked not applicable/unresolved.
-5. Every REQ and material CTRL state has acceptance, external confirmation, decision or explicit exception.
-6. Derived/delegated/evidence-backed items have traceable basis and no hidden product expansion.
-7. Non-goals, forbidden shortcuts, risks and recovery are concrete.
-8. No unsupported number, threshold, metric or external claim appears.
-9. Selected design resources retain stable identity and exact declared coverage; candidates remain non-authoritative.
-10. The Source is self-contained enough for Contract authoring and names every still-required external artifact.
-
-Then add non-rendering `ty-source-item:start/end` markers to the real Markdown Source without rewriting direct text, and proceed to `contract-authoring.md`. The markers and Contract mapping are part of this same Long-Task authoring loop.
+# Source-Bound Draft Input Reference
+
+Read this alongside `contract-authoring.md` when raw, mixed, attachment-heavy or incomplete inputs need Source-quality repair while the same Contract Draft is being mapped. Inputs enter the Draft immediately; this reference is neither an earlier Source-authoring phase nor a standalone Source Plan stage or second lifecycle.
+
+## Objective and boundary
+
+Preserve every material user, product, technical, visual and acceptance constraint from the initial/revised proposal and supplied resources. Add only traceable necessary derivations, defensible delegated choices and evidence-backed repository facts. Make the real Source understandable without the original conversation before Preflight/Compile, while allowing Draft decomposition and repository binding to proceed incrementally.
+
+Do not create a Source Plan schema, CLI, Preflight, Compile, Receipt, cache, authority, state or internal Source-authoring stage. Contract YAML cannot become the sole owner of a choice or missing semantic. Do not let current implementation silently redefine intent. A pre-existing Source Plan is simply one possible input.
+
+## Input inventory
+
+1. Assign every proposal, selected design resource, screenshot, document, diagram, table and other attachment a stable input ID.
+2. Inspect all material pages/frames/screens/tables/visible states; never silently sample a multi-part artifact.
+3. Classify each input as user instruction, product requirement, technical constraint, existing proposal, selected target, repository/Context evidence, constraint, inspiration or background.
+4. For visual resources, preserve selection basis, classification (`exact-target`, `constraint` or `inspiration`), stable resource/surface/control/state/target keys, declared platform/viewport/mode/state/content applicability, source profile/canonical entry/dependency set, provider/project/run/entry provenance and immutable digest/snapshot, plus typed locators. A mutable link, metadata-only response, partial file set or prose locator is incomplete. Unselected candidates authorize no fidelity.
+5. Record incorporated meaning and every unreadable, conflicting or intentionally unused part. Higher authority and user-stated precedence win; unresolved conflicts remain decisions.
+
+## Preference and research gate
+
+Before comparative research or a material product, technical, architecture or provider selection, identify decision-changing criteria such as fidelity versus cost, delivery speed, reliability/support, privacy/compliance, lock-in/control, operational burden, platform scope and extensibility.
+
+Infer preferences only from user words, Source, Context or controlling constraints. If an unknown preference would materially change research or recommendation, ask one concise targeted clarification before proceeding. Do not impose a questionnaire, re-ask known preferences or pause for minor reversible choices with the same defensible recommendation.
+
+Use current primary/authoritative evidence for changing external facts. Record source, scope and retrieval date. Preference clarification authorizes plan meaning, not payment, contracting, deployment/publication, destructive production mutation, permission grants, sensitive-data transmission or required legal/security/human approval; those remain typed external confirmations.
+
+## Working strategies, not phases
+
+Choose locally as needed while revising the same Draft; do not expose these as lifecycle stages or ask the user to choose:
+
+- **refinement:** preserve and complete a substantially developed proposal;
+- **synthesis:** build coherent Source from a goal plus mixed inputs;
+- **hybrid:** use one proposal as backbone and fill gaps from other inputs.
+
+A short request is sufficient when roles, goal and reference authority are recoverable. Reuse an authorized writable proposal as the real Source. If the delivery exists only in conversation, materialize exactly one project-native Markdown Source according to repository convention. Do not create a parallel planning artifact.
+
+## Semantic authoring
+
+For every material item, preserve one origin:
+
+- `direct`: stated by user or controlling input, with all qualifiers;
+- `derived`: unavoidable for completeness/falsifiability, identifies `Derived From`, states why necessary and changes no user capability, business rule or scope;
+- `delegated`: a defensible choice requested by instructions to synthesize/refine/use judgment, records `Delegated By`, preference/evidence basis and exact added meaning;
+- `evidence-backed`: repository/Context fact with exact source and no promotion of incidental code shape to product intent;
+- `decision_required`: conflicting authority, explicitly user-reserved choice, missing material preference or no defensible recommendation.
+
+High impact or several options is not itself a reason to pause when criteria support one recommendation. Keep real high-risk actions as external confirmations. Never introduce a requirement for the first time only inside acceptance criteria.
+
+## Structure and stable keys
+
+Use stable semantic lowercase-kebab keys and Markdown anchors where practical. Preserve keys when wording changes but meaning does not; never renumber for ordering or reuse a retired key for new meaning.
+
+Define vertical Outcomes only when observable results are independently decidable and later verifiable. Do not split by response length, frontend/backend layer, module count, agent capacity or desired parallelism; do not merge distinct results merely for brevity.
+
+Use only applicable semantic types:
+
+- result/Outcome;
+- Requirement (`REQ`);
+- user-visible Control (`CTRL`);
+- technical obligation (`OBL`);
+- explicitly non-completing meaning (`NCOMP`);
+- acceptance scenario (`AC`);
+- global non-goal/constraint and forbidden shortcut;
+- risk with exact Fact, Affected Outcome, Basis and Consequence;
+- external confirmation (`EXT`);
+- genuine decision (`DEC`);
+- advisory implementation hint (`HINT`), which is not a material requirement.
+
+## UI and control completeness
+
+For each in-scope surface, record purpose, entry/exit/navigation, regions/overlays and included Control keys. For every material interactive control, independently preserve applicable:
+
+`surface`, `region`, `control type`, `label/content`, `location`, `user task`, `visibility`, `availability`, `trigger`, `input`, `validation`, `default`, `interaction`, `navigation/result`, `loading`, `empty`, `success`, `failure`, `recovery`, `permission`, `feedback` and `accessibility`.
+
+Do not invent controls for a non-interface delivery. A coarse frame or configured design system does not supply unshown states. Selected design resources and product/technical Source remain parallel: visuals cannot invent business/data/permission/algorithmic rules.
+
+For every selected exact/constraint target, preserve the declared platform/viewport/mode/state/content conditions and identify which surface and Control keys it governs. Separately record any design-resource acceptance blocker supplied by the Source. File identity, hashes, provider/export success, registry membership and resource counts are integrity facts only; they do not state that a production owner, real-user journey or rendered interaction conforms.
+
+## Acceptance and risk
+
+Each AC has exactly one Given/When/Then scenario, names the REQ/CTRL/OBL/NCOMP meaning it accepts and introduces no undeclared product semantics. Keep representative/sample/framework checks distinct from full-population claims and partial delivery distinct from completion.
+
+Use the Runtime's exact risk Fact names when marking risk. Data migration is `data_migration`; a weakly observable critical path is separate `critical_user_path` and `weak_observability` facts; preserve `multi_repository_change` in Source so Contract compilation can reject unsupported delivery honestly.
+
+## Preflight/Compile convergence audit
+
+Before Preflight/Compile confirm:
+
+1. Every material original statement and qualifier is preserved.
+2. Every supplied input is incorporated or has an explicit unreadable/unused/conflict disposition.
+3. Distinct requirements and independently decidable Outcomes were not collapsed.
+4. Every material UI surface/control/state is explicit or marked not applicable/unresolved.
+5. Every REQ and material CTRL state has acceptance, external confirmation, decision or explicit exception.
+6. Derived/delegated/evidence-backed items have traceable basis and no hidden product expansion.
+7. Non-goals, forbidden shortcuts, risks and recovery are concrete.
+8. No unsupported number, threshold, metric or external claim appears.
+9. Selected design resources retain stable identity and exact declared coverage; candidates remain non-authoritative.
+10. Every material UI surface/control can be mapped to a production target/owner, real-user entry journey and acceptance route, while every declared design blocker has an explicit machine or target-blocking external-confirmation disposition. Removing one from scope requires an explicit Source revision; Contract prose cannot waive it.
+11. The Source is self-contained enough to own every mapped Draft semantic and names every still-required external artifact.
+
+Complete non-rendering `ty-source-item:start/end` markers in the real Markdown Source without rewriting direct text, and finish the corresponding Contract mapping in the same loop. Neither markers nor this audit delay opening the Draft; all are fail-closed convergence requirements before Preflight/Compile.

package/assets/skills/normal-long-task/SKILL.md

@@ -1,12 +1,12 @@
----
-name: normal-long-task
-description: Retired compatibility pointer for users who explicitly invoke /normal-long-task. Direct them to /long-task-workflow and do not create legacy checklist, prompt, audit, matrix, verdict, or plan artifacts.
----
-
-# Retired: Normal Long Task
-
-`/normal-long-task` no longer defines a second long-task artifact workflow.
-
-Use `/long-task-workflow` for one Canonical Delivery Contract, the current platform-native Goal, rolling implementation in the current workspace, targeted repair verification, a same-snapshot Final Gate and Stop freshness.
-
-Do not create a preserved-source/checklist pair, target-mode prompt, Local Audit, matrix, verdict or second plan from this compatibility invocation.
+---
+name: normal-long-task
+description: Retired compatibility pointer for users who explicitly invoke /normal-long-task. Direct them to /long-task-workflow and do not create legacy checklist, prompt, audit, matrix, verdict, or plan artifacts.
+---
+
+# Retired: Normal Long Task
+
+`/normal-long-task` no longer defines a second long-task artifact workflow.
+
+Use `/long-task-workflow` for one Canonical Delivery Contract, the current platform-native Goal, rolling implementation in the current workspace, targeted repair verification, a same-snapshot Final Gate and Stop freshness.
+
+Do not create a preserved-source/checklist pair, target-mode prompt, Local Audit, matrix, verdict or second plan from this compatibility invocation.

package/assets/skills/source-plan-authoring/SKILL.md

@@ -1,14 +1,14 @@
----
-name: source-plan-authoring
-description: Retired compatibility pointer for users who explicitly invoke /source-plan-authoring or request the former standalone Source Plan stage. Direct long deliveries to /long-task-workflow, whose integrated Source authoring now consumes raw or revised proposals, selected design resources and mixed attachments before Contract Draft authoring. Do not create a legacy standalone Source Plan workflow, gate, schema, state or second plan.
----
-
-# Retired: Source Plan Authoring
-
-`/source-plan-authoring` no longer defines a separate handoff between the initial proposal and Long-Task execution.
-
-For an explicit long delivery, invoke `/long-task-workflow` with the initial/revised proposal, selected immutable design resources and other attachments. It now owns input inventory, Source-quality synthesis/refinement, stable semantic keys, control-level UI meaning, acceptance scenarios, research/delegation traceability, real Source marking, repository binding and the same `delivery-contract.yaml` Draft in one Goal.
-
-For non-long work, give the proposal and selected resources directly to the current native Goal under the default Workflow Contract. If the user only wants an initial product or technical proposal, use the applicable proposal-authoring capability rather than recreating this retired intermediary.
-
-A pre-existing Source Plan remains valid ordinary Source. Do not rewrite it merely for compatibility, create a new Source Plan artifact, invoke Long-Task automatically, or create a second plan, Contract Draft, Preflight, Compile, Receipt, Authority or state surface from this pointer.
+---
+name: source-plan-authoring
+description: Retired compatibility pointer for users who explicitly invoke /source-plan-authoring or request the former standalone Source Plan stage. Direct long deliveries to /long-task-workflow, where raw or revised proposals, selected design resources and mixed attachments enter one Source-bound Contract Draft loop immediately. Do not create a legacy standalone Source Plan or internal Source-authoring stage, gate, schema, state or second plan.
+---
+
+# Retired: Source Plan Authoring
+
+`/source-plan-authoring` no longer defines a separate handoff between the initial proposal and Long-Task execution.
+
+For an explicit long delivery, invoke `/long-task-workflow` with the initial/revised proposal, selected immutable design resources and other attachments. They enter the same `delivery-contract.yaml` Draft immediately; input inventory, Source-quality synthesis/refinement, stable semantic keys, control-level UI meaning, acceptance scenarios, research/delegation traceability, real Source marking, repository binding and Contract mapping converge in one Goal before Preflight/Compile.
+
+For non-long work, give the proposal and selected resources directly to the current native Goal under the default Workflow Contract. If the user only wants an initial product or technical proposal, use the applicable proposal-authoring capability rather than recreating this retired intermediary.
+
+A pre-existing Source Plan remains valid ordinary Source. Do not rewrite it merely for compatibility, create a new Source Plan artifact, invoke Long-Task automatically, or create a second plan, Contract Draft, Preflight, Compile, Receipt, Authority or state surface from this pointer.