project-tiny-context-harness 0.7.5 → 0.7.7

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

@@ -1,84 +1,85 @@
----
-name: long-task-workflow
-description: Author, preflight, execute, resume, verify, or close one complete Single-Goal Delivery Contract in the current native Goal and workspace. Use only when explicitly invoked or a valid common-dir active authority binding exists.
----
-
-# Single-Goal Long-Task Workflow
-
-## Boundaries
-
-Use one current native Goal, one repository, one selected workspace, one complete Contract and one Final Gate. Never create a scheduler, model worker, agent runtime, App Server, branch, worktree, merge, push, PR, deployment, Campaign/SFC/Packet/Wave chain, matrix, verdict or second Contract plan. Never activate from task size alone.
-
-The host and user own model selection and native-Goal lifecycle. The workflow has exactly one user-choice checkpoint after the first Authority Lock and before implementation; Harness neither switches the model nor persists model-routing/checkpoint state. No checkpoint file, acknowledgement state, model route, model-tier scheduler, automatic model switch, `authority_revision_in_progress` state or native-Goal completion state is created. Outside that boundary, do not pause a healthy Goal solely to change or downgrade the model. Do not create a separate approval checkpoint for a defensible recommended plan choice. A targeted pre-Authority clarification is still required when a missing user preference could materially change research or selection; genuine Source conflicts or choices the user explicitly reserves may likewise require a decision before Authority Lock. Capability-related drift is handled by targeted repair plus the Final Gate. Never proactively spawn, assign or coordinate parallel subagents. Platform-native internal delegation, if it occurs, is opaque and non-authoritative and must converge into the unified current workspace snapshot before verification can count.
-
-`long-task-delivery-v2` is the only active Contract schema. `delivery-contract.yaml` is the root authoring file. New authoring uses inline Outcomes; existing `outcome_files` are physical compatibility only. `delivery-set` is retired and non-executing.
-
-## Controlling Objective
-
-Prevent false completion inside declared authority. Implementation may drift, fail or require rework, but every declared non-Result requirement and AC must remain traceable and every unsatisfied, unverifiable, insufficiently evidenced or stale item must block completion. In particular, a proxy target, presence text, degradation path, fixed input, self-reported boundary effect or internal entrypoint must never substitute for the declared target behavior. Findings should localize repair through Source Item, Stage, Outcome, Claim, Assertion, Check, Evidence Capability, execution target, Binding and owner boundary.
-
-Only fresh evidence from the complete current final snapshot may create machine acceptance. Otherwise report the task as unfinished or qualified. `machine_accepted_external_pending` means machine-verifiable authority passed while named external confirmation remains; it is not full delivery completion. Machine acceptance covers declared machine Authority and has no direct native-Goal effect. Never substitute prose, progress, historical tests, Receipts, one exit code or Agent judgment for the Final Gate.
-
-Prefer the lowest practical Authoring, Runtime, State, Recovery and verification cost that preserves the same false-completion interception. Add no mechanism whose distinct protection does not materially exceed its total cost.
-
-## Progressive Reference Loading
-
-Read only the reference needed for the current phase; these files are guidance, not new artifacts or authority:
-
-- Before creating or structurally revising Source markers, Outcomes, requirements, controls, obligations, architecture boundaries, paths, Bindings, Assertions or risk, read [`references/contract-authoring.md`](references/contract-authoring.md).
-- Before creating or repairing Checks, runners, Observations, proof surfaces, Playwright/structured evidence, Counterfactuals, Population or environment probes, read [`references/evidence-design.md`](references/evidence-design.md).
-- Before Preflight, Compile, protected revision, resume, targeted verify, Final Gate, Stop, close or abandon, read [`references/authority-lifecycle.md`](references/authority-lifecycle.md).
-
-Do not copy reference detail into another plan or state file. The same `delivery-contract.yaml`, active authority and current workspace remain the only lifecycle surfaces.
-
-## Contract Draft And Outcome Decomposition
-
-Before the first successful formal Compile, continuously revise the same non-authoritative `delivery-contract.yaml` as the Contract Draft. It need not be completed in one response; keep reading Source, repository and relevant Context and feed Preflight findings back into that same Draft. Draft authoring, Preflight, Compile, rolling execution, targeted verification and Final Gate are one `long-task-workflow` lifecycle. Do not create a standalone Contract Draft Skill, Draft Receipt, Authoring State, draft schema/CLI/runtime state or second plan.
-
-A Draft Outcome is an Outcome in that pre-Authority-Lock Draft, not a new schema field or runtime entity. Decompose only vertical, independently observable, decidable and target-verifiable results whose dependencies and owner boundary can be stated; one Outcome belongs to one declared Stage and does not span materially different success paths. Declare the ordered Stage DAG and one gate Outcome per Stage in the same Contract. Use those boundaries to keep a stage-constrained dependency-ready working set, target verification, localize failures, resume findings/next actions and stale local results precisely.
-
-`depends_on` means acceptance readiness. The gate Outcome transitively depends on the rest of its Stage, later Stage Outcomes depend on prerequisite gate Outcomes, and every multi-Outcome gate proves cross-surface consistency. The current Goal derives a temporary Rolling Frontier from Stage and Outcome status, but must not persist a Stage Receipt, scheduler, Worker queue, mandatory implementation DAG, model route or process tree. Never split for response/YAML/file length, implementation layer, module/file count, Agent capacity, Worker assignment or desired parallelism.
-
-> Outcome decomposes execution and diagnosis, not completion authority.
-
-## Entry And Authoring Loop
-
+---
+name: long-task-workflow
+description: Author, preflight, execute, resume, verify, or close one complete Single-Goal Delivery Contract in the current native Goal and workspace. Use only when explicitly invoked or a valid common-dir active authority binding exists.
+---
+
+# Single-Goal Long-Task Workflow
+
+## Boundaries
+
+Use one current native Goal, one repository, one selected workspace, one complete Contract and one Final Gate. Never create a scheduler, model worker, agent runtime, App Server, branch, worktree, merge, push, PR, deployment, Campaign/SFC/Packet/Wave chain, matrix, verdict or second Contract plan. Never activate from task size alone.
+
+The host and user own model selection and native-Goal lifecycle. The workflow has exactly one user-choice checkpoint after the first Authority Lock and before implementation; Harness neither switches the model nor persists model-routing/checkpoint state. No checkpoint file, acknowledgement state, model route, model-tier scheduler, automatic model switch, `authority_revision_in_progress` state or native-Goal completion state is created. Outside that boundary, do not pause a healthy Goal solely to change or downgrade the model. Do not create a separate approval checkpoint for a defensible recommended plan choice. A targeted pre-Authority clarification is still required when a missing user preference could materially change research or selection; genuine Source conflicts or choices the user explicitly reserves may likewise require a decision before Authority Lock. Capability-related drift is handled by targeted repair plus the Final Gate. Never proactively spawn, assign or coordinate parallel subagents. Platform-native internal delegation, if it occurs, is opaque and non-authoritative and must converge into the unified current workspace snapshot before verification can count.
+
+`long-task-delivery-v2` is the only active Contract schema. `delivery-contract.yaml` is the root authoring file. New authoring uses inline Outcomes; existing `outcome_files` are physical compatibility only. `delivery-set` is retired and non-executing.
+
+## Controlling Objective
+
+Prevent false completion inside declared authority. Implementation may drift, fail or require rework, but every declared non-Result requirement and AC must remain traceable and every unsatisfied, unverifiable, insufficiently evidenced or stale item must block completion. In particular, a proxy target, presence text, degradation path, fixed input, self-reported boundary effect or internal entrypoint must never substitute for the declared target behavior. Findings should localize repair through Source Item, Stage, Outcome, Claim, Assertion, Check, Evidence Capability, execution target, Binding and owner boundary.
+
+Only fresh evidence from the complete current final snapshot may create machine acceptance. Otherwise report the task as unfinished or qualified. `machine_accepted_external_pending` means machine-verifiable authority passed while named external confirmation remains; it is not full delivery completion. Machine acceptance covers declared machine Authority and has no direct native-Goal effect. Never substitute prose, progress, historical tests, Receipts, one exit code or Agent judgment for the Final Gate.
+
+Prefer the lowest practical Authoring, Runtime, State, Recovery and verification cost that preserves the same false-completion interception. Add no mechanism whose distinct protection does not materially exceed its total cost.
+
+## Progressive Reference Loading
+
+Read only the reference needed for the current phase; these files are guidance, not new artifacts or authority:
+
+- Before creating or structurally revising Source markers, Outcomes, requirements, controls, obligations, architecture boundaries, paths, Bindings, Assertions or risk, read [`references/contract-authoring.md`](references/contract-authoring.md).
+- Before creating or repairing Checks, runners, Observations, proof surfaces, Playwright/structured evidence, Counterfactuals, Population or environment probes, read [`references/evidence-design.md`](references/evidence-design.md).
+- Before Preflight, Compile, protected revision, resume, targeted verify, Final Gate, Stop, close or abandon, read [`references/authority-lifecycle.md`](references/authority-lifecycle.md).
+
+Do not copy reference detail into another plan or state file. The same `delivery-contract.yaml`, active authority and current workspace remain the only lifecycle surfaces.
+
+## Contract Draft And Outcome Decomposition
+
+Before the first successful formal Compile, continuously revise the same non-authoritative `delivery-contract.yaml` as the Contract Draft. It need not be completed in one response; keep reading Source, repository and relevant Context and feed Preflight findings back into that same Draft. Draft authoring, Preflight, Compile, rolling execution, targeted verification and Final Gate are one `long-task-workflow` lifecycle. Do not create a standalone Contract Draft Skill, Draft Receipt, Authoring State, draft schema/CLI/runtime state or second plan.
+
+A Draft Outcome is an Outcome in that pre-Authority-Lock Draft, not a new schema field or runtime entity. Decompose only vertical, independently observable, decidable and target-verifiable results whose dependencies and owner boundary can be stated; one Outcome belongs to one declared Stage and does not span materially different success paths. Declare the ordered Stage DAG and one gate Outcome per Stage in the same Contract. Use those boundaries to keep a stage-constrained dependency-ready working set, target verification, localize failures, resume findings/next actions and stale local results precisely.
+
+`depends_on` means acceptance readiness. The gate Outcome transitively depends on the rest of its Stage, later Stage Outcomes depend on prerequisite gate Outcomes, and every multi-Outcome gate proves cross-surface consistency. The current Goal derives a temporary Rolling Frontier from Stage and Outcome status, but must not persist a Stage Receipt, scheduler, Worker queue, mandatory implementation DAG, model route or process tree. Never split for response/YAML/file length, implementation layer, module/file count, Agent capacity, Worker assignment or desired parallelism.
+
+> Outcome decomposes execution and diagnosis, not completion authority.
+
+## Entry And Authoring Loop
+
 1. Read the user request or external proposal plus minimum controlling Context and decide `Context Delta: none|required`.
    - For material production UI, read the Contract-authoring visual guidance before Compile. Inspect any external design resources as ordinary Source, including selection basis, stable identity and declared surface/viewport/mode/state coverage. An unconfigured starter, candidate, style-only rule or inspiration-only reference is incomplete design authority unless Source explicitly scopes the result as prototype/non-fidelity or supplies a selected target before implementation.
-2. If a valid active binding exists, run `ty-context long-task resume <workdir>` and read the lifecycle reference.
-3. Otherwise author one complete Delivery Contract for the whole selected delivery. Declare the target profile, its non-empty required product target refs, each target's runtime family/root entrypoint, ordered Stages and vertical Outcomes. Do not create a second Contract plan, matrix or top-level Contract split.
-4. Preserve at least one real `source_path`. Wrap every material Source item in its original Markdown with non-rendering `ty-source-item:start/end` markers without rewriting the text; marked Source Item keys and `source_claim` keys are exactly equal.
+   - If the user is asking to generate or iterate standalone design resources before Contract authoring rather than execute this delivery, use `design-resource-authoring` instead. Its result may later return as ordinary Source; it creates no Contract Draft or Authority.
+2. If a valid active binding exists, run `ty-context long-task resume <workdir>` and read the lifecycle reference.
+3. Otherwise author one complete Delivery Contract for the whole selected delivery. Declare the target profile, its non-empty required product target refs, each target's runtime family/root entrypoint, ordered Stages and vertical Outcomes. Do not create a second Contract plan, matrix or top-level Contract split.
+4. Preserve at least one real `source_path`. Wrap every material Source item in its original Markdown with non-rendering `ty-source-item:start/end` markers without rewriting the text; marked Source Item keys and `source_claim` keys are exactly equal.
 5. An ordinary prose plan, optional Source Plan or externally authored design resource remains valid Source after marker-only enumeration and does not need to match a recommended authoring structure. Preserve stable semantic keys and Markdown anchors where practical. External design authoring neither updates Context nor creates Contract authority by itself; candidate resources authorize no fidelity Claim.
-6. Continue reading repository, Source and Context and revise the same Draft. A request to synthesize, refine, complete, implement or use judgment delegates plan-level authoring, but it does not invent the user's tradeoff priorities. Before comparative research or a material product, technical, architecture or provider selection, identify the criteria that could change the research scope, candidate set or recommendation. Infer them only from the user's words, Source, Context or controlling constraints. If quality versus cost, speed, reliability, privacy, lock-in, operational burden or another material priority is unknown or ambiguous, stop before that research or selection and ask one concise targeted clarification. Do not impose a questionnaire, re-ask known preferences or interrupt minor reversible choices whose recommendation would not change.
-7. Once the material preference envelope is clear, decide what research is needed. Use current authoritative or primary evidence for external capability, pricing, quota, license, compatibility, region, security posture or support claims. When one recommendation is then defensible, record it in real Source with the authoring instruction, preference/evidence basis and exact added meaning instead of pausing for approval. Append the delegated item without rewriting the user's original text when ordinary prose is the Source. Return only when authoritative requirements conflict, the user explicitly reserves the choice, a material preference remains unknown, critical semantics have no defensible recommendation or no falsifiable acceptance standard can be formed.
-8. Contract expansion remains limited to meaning-preserving structural decomposition, evidence-backed repository binding and choices first recorded as delegated real Source. Never place a new product rule, default, threshold, recovery behavior, permission or platform/data scope only in Contract YAML. Default plan delegation authorizes meaning, not action: payment, contracting, production deployment or publication, destructive production mutation, real permission grants, sensitive-data transmission and required legal/security/human approval remain named external confirmations. Any conflicting, user-reserved, missing-preference or unsupported semantic remains `decision_required`.
-9. Give every Check an atomic Given/When scenario and journey role; give every Assertion the minimum all-of Evidence Capabilities that can actually prove its Claim. Separate required success and degradation Checks. Type every external confirmation with impacted Claim refs and target-blocking effect. Run read-only `ty-context long-task preflight <workdir>`, repair every error and `decision_required` finding in the same Draft, then formally Compile only when ready.
-10. When the first Compile returns `execution_model_checkpoint.required: true`, stop before implementation and ask the user to choose `continue_current_model` or switch models and then resume the active Long-Task. A task-specific choice already stated explicitly satisfies the checkpoint. Later revisions return `required: false` and do not repeat it.
-
-Architecture quality uses the existing authority model, not a new gate: when Source or controlling Context declares an architecture invariant, encode it as a Source-backed technical obligation/global constraint/forbidden shortcut plus owner/path/Binding boundaries and a project-owned executable Check. Functional acceptance cannot substitute when the architecture claim can fail independently. An unverifiable design preference remains task-local, durable Context or `decision_required`; it must not be promoted into false proof.
-
-## Rolling Execution
-
-After Authority Lock and the one-time execution-model checkpoint are satisfied, implement only Outcomes in the derived current Stage frontier, plus prerequisite regression repairs and current Finding repairs, in the current workspace. A later Stage cannot substitute for an unpassed earlier gate. Small implementation plans and repair hypotheses are internal execution state and cannot silently change Product, Technical or Acceptance authority.
-
-Re-evaluate `Context Delta` whenever implementation or repair discovers a durable fact. Controlling Context changes use protected revision; graph-derived, non-explicit `implementation-index` and `archive` are Supporting Context in referenced mode and may auto-revise when only navigation/background changed. Full snapshot mode treats every selected Context file as controlling.
-
-Use targeted `verify --outcome/--check` only to drive repair. Progress is repair evidence only and never acceptance authority. Keep precise findings attached to the owning Source item, Claim, Assertion, Check, Binding and owner path. Do not add another model-switch pause or coordinate parallel subagents.
-
-When the Contract declares a target-runtime Check because a proxy can pass while the target fails independently, run it at the earliest owning Outcome's first runnable boundary. Every required target is proved separately from its root; Browser evidence requires Playwright and Native/Desktop evidence requires the project binary. After accumulated changes to declared `input_paths` or Binding carriers make the result stale, rerun before dependent work grows. Coalesce related edits and use the cheapest reliable target Check; do not mandate a full environment rebuild per Outcome or per edit. This is rolling feedback through existing targeted verify, not acceptance, a trigger queue or per-target progress state.
-
-When implementation discovers a blocker or missing Contract paths, first classify the revision. Difficulty or delay alone never reclassifies machine-verifiable scope as external and never removes Source; a real scope, Product, Acceptance or machine/external boundary change must first be explicit marked Source. Proven monotonic evidence strengthening may use ordinary `compile --revise` directly. If every protected reason is only owner/expected-change/allowed-support expansion, continue editing the same `delivery-contract.yaml` and use `ty-context long-task diagnose-revision <workdir> [--outcome <key>] [--check <key>]` to exercise only existing active Check identities with unchanged runner/verifier authority; safe monotonic strengthening may coexist. Candidate diagnostics are transient: they authorize no acceptance and write no pending/approval state, Active Authority, cache, Progress or Receipt. Semantic changes, proof weakening, runner or verifier-content changes, and risk-increase candidates are preview-only and must not run; risk downgrade is rejected. When the candidate is complete, run ordinary `compile --revise` once, present its exact material decision summary to the user, and never approve it yourself. Keep the previous Authority active until exact approval and atomic adoption. Adoption is not delivery completion: discard historical/candidate evidence, run `status` or `resume`, and return to rolling implementation or repair under the revised Authority before Final Gate.
-
-## Live Final Authority
-
-Complete Context, implementation and project tests, create a clean candidate commit, then run `ty-context long-task final-gate <workdir>`.
-
-Final Gate recompiles Source authority, validates active task/revision/compiled/worktree identity, creates one Git-tree snapshot, reruns every required Global and Outcome Check and rechecks active identity before acceptance. It derives Stage results and target qualification from that run; it does not trust targeted Progress as a Stage pass. A target-runtime Check must exercise its exact target in that current Gate execution; rerunning a reader for a historical or tracked status report is not live target proof. Final Gate, Stop and close never trust historical Progress, Receipt or compiled cache.
-
-Machine acceptance covers only declared machine authority. Preserve every pending external confirmation through `final-gate`, `status`, `resume`, `stop-check`, the package-owned Stop Hook and `close`; accepted output identifies `acceptance_scope: declared_machine_authority` and `native_goal_effect: none`, while `closed_scope: machine_authority` means only Authority cleanup. Do not invent external-confirmation or native-Goal tracking state.
-
-Before invoking platform-native Goal completion, perform one veto-only conformance review: compare the current Goal and user instructions with accepted marked Source, and check for pending revisions, unresolved blockers or omitted requirements. Any mismatch keeps the Goal active and returns to Source/Contract repair. A clean review does not add acceptance proof and never lets Agent judgment replace Final Gate.
-
-## Handoff
-
-Report implementation, effective risk, Claim Coverage, Stage frontier/results, declared target profile, exact `target_state`, Live Gate result, acceptance scope, every pending external confirmation, Context status and blockers. Use verifier terms exactly: `progress_passing` means targeted repair evidence, `progress_stale` is not a current pass, `final_workflow_status: null` means unfinished, `authority_revision_adopted` means return to rolling execution, and `machine_accepted_external_pending` must retain its named confirmations. Contract target states are only `implementation_complete`, `target_profile_usable` and `production_release_ready`; terminal failure uses `not_accepted` or `blocked_external`. Never shorten targeted progress to “Outcome complete” or invent per-platform progress/status. State the threat-model limits: undeclared requirements cannot be discovered, installed verifier/Git metadata are trusted, native-Goal/model selection belongs to the host/user, and internal platform delegation is not observed.
+6. Continue reading repository, Source and Context and revise the same Draft. A request to synthesize, refine, complete, implement or use judgment delegates plan-level authoring, but it does not invent the user's tradeoff priorities. Before comparative research or a material product, technical, architecture or provider selection, identify the criteria that could change the research scope, candidate set or recommendation. Infer them only from the user's words, Source, Context or controlling constraints. If quality versus cost, speed, reliability, privacy, lock-in, operational burden or another material priority is unknown or ambiguous, stop before that research or selection and ask one concise targeted clarification. Do not impose a questionnaire, re-ask known preferences or interrupt minor reversible choices whose recommendation would not change.
+7. Once the material preference envelope is clear, decide what research is needed. Use current authoritative or primary evidence for external capability, pricing, quota, license, compatibility, region, security posture or support claims. When one recommendation is then defensible, record it in real Source with the authoring instruction, preference/evidence basis and exact added meaning instead of pausing for approval. Append the delegated item without rewriting the user's original text when ordinary prose is the Source. Return only when authoritative requirements conflict, the user explicitly reserves the choice, a material preference remains unknown, critical semantics have no defensible recommendation or no falsifiable acceptance standard can be formed.
+8. Contract expansion remains limited to meaning-preserving structural decomposition, evidence-backed repository binding and choices first recorded as delegated real Source. Never place a new product rule, default, threshold, recovery behavior, permission or platform/data scope only in Contract YAML. Default plan delegation authorizes meaning, not action: payment, contracting, production deployment or publication, destructive production mutation, real permission grants, sensitive-data transmission and required legal/security/human approval remain named external confirmations. Any conflicting, user-reserved, missing-preference or unsupported semantic remains `decision_required`.
+9. Give every Check an atomic Given/When scenario and journey role; give every Assertion the minimum all-of Evidence Capabilities that can actually prove its Claim. Separate required success and degradation Checks. Type every external confirmation with impacted Claim refs and target-blocking effect. Run read-only `ty-context long-task preflight <workdir>`, repair every error and `decision_required` finding in the same Draft, then formally Compile only when ready.
+10. When the first Compile returns `execution_model_checkpoint.required: true`, stop before implementation and ask the user to choose `continue_current_model` or switch models and then resume the active Long-Task. A task-specific choice already stated explicitly satisfies the checkpoint. Later revisions return `required: false` and do not repeat it.
+
+Architecture quality uses the existing authority model, not a new gate: when Source or controlling Context declares an architecture invariant, encode it as a Source-backed technical obligation/global constraint/forbidden shortcut plus owner/path/Binding boundaries and a project-owned executable Check. Functional acceptance cannot substitute when the architecture claim can fail independently. An unverifiable design preference remains task-local, durable Context or `decision_required`; it must not be promoted into false proof.
+
+## Rolling Execution
+
+After Authority Lock and the one-time execution-model checkpoint are satisfied, implement only Outcomes in the derived current Stage frontier, plus prerequisite regression repairs and current Finding repairs, in the current workspace. A later Stage cannot substitute for an unpassed earlier gate. Small implementation plans and repair hypotheses are internal execution state and cannot silently change Product, Technical or Acceptance authority.
+
+Re-evaluate `Context Delta` whenever implementation or repair discovers a durable fact. Controlling Context changes use protected revision; graph-derived, non-explicit `implementation-index` and `archive` are Supporting Context in referenced mode and may auto-revise when only navigation/background changed. Full snapshot mode treats every selected Context file as controlling.
+
+Use targeted `verify --outcome/--check` only to drive repair. Progress is repair evidence only and never acceptance authority. Keep precise findings attached to the owning Source item, Claim, Assertion, Check, Binding and owner path. Do not add another model-switch pause or coordinate parallel subagents.
+
+When the Contract declares a target-runtime Check because a proxy can pass while the target fails independently, run it at the earliest owning Outcome's first runnable boundary. Every required target is proved separately from its root; Browser evidence requires Playwright and Native/Desktop evidence requires the project binary. After accumulated changes to declared `input_paths` or Binding carriers make the result stale, rerun before dependent work grows. Coalesce related edits and use the cheapest reliable target Check; do not mandate a full environment rebuild per Outcome or per edit. This is rolling feedback through existing targeted verify, not acceptance, a trigger queue or per-target progress state.
+
+When implementation discovers a blocker or missing Contract paths, first classify the revision. Difficulty or delay alone never reclassifies machine-verifiable scope as external and never removes Source; a real scope, Product, Acceptance or machine/external boundary change must first be explicit marked Source. Proven monotonic evidence strengthening may use ordinary `compile --revise` directly. If every protected reason is only owner/expected-change/allowed-support expansion, continue editing the same `delivery-contract.yaml` and use `ty-context long-task diagnose-revision <workdir> [--outcome <key>] [--check <key>]` to exercise only existing active Check identities with unchanged runner/verifier authority; safe monotonic strengthening may coexist. Candidate diagnostics are transient: they authorize no acceptance and write no pending/approval state, Active Authority, cache, Progress or Receipt. Semantic changes, proof weakening, runner or verifier-content changes, and risk-increase candidates are preview-only and must not run; risk downgrade is rejected. When the candidate is complete, run ordinary `compile --revise` once, present its exact material decision summary to the user, and never approve it yourself. Keep the previous Authority active until exact approval and atomic adoption. Adoption is not delivery completion: discard historical/candidate evidence, run `status` or `resume`, and return to rolling implementation or repair under the revised Authority before Final Gate.
+
+## Live Final Authority
+
+Complete Context, implementation and project tests, create a clean candidate commit, then run `ty-context long-task final-gate <workdir>`.
+
+Final Gate recompiles Source authority, validates active task/revision/compiled/worktree identity, creates one Git-tree snapshot, reruns every required Global and Outcome Check and rechecks active identity before acceptance. It derives Stage results and target qualification from that run; it does not trust targeted Progress as a Stage pass. A target-runtime Check must exercise its exact target in that current Gate execution; rerunning a reader for a historical or tracked status report is not live target proof. Final Gate, Stop and close never trust historical Progress, Receipt or compiled cache.
+
+Machine acceptance covers only declared machine authority. Preserve every pending external confirmation through `final-gate`, `status`, `resume`, `stop-check`, the package-owned Stop Hook and `close`; accepted output identifies `acceptance_scope: declared_machine_authority` and `native_goal_effect: none`, while `closed_scope: machine_authority` means only Authority cleanup. Do not invent external-confirmation or native-Goal tracking state.
+
+Before invoking platform-native Goal completion, perform one veto-only conformance review: compare the current Goal and user instructions with accepted marked Source, and check for pending revisions, unresolved blockers or omitted requirements. Any mismatch keeps the Goal active and returns to Source/Contract repair. A clean review does not add acceptance proof and never lets Agent judgment replace Final Gate.
+
+## Handoff
+
+Report implementation, effective risk, Claim Coverage, Stage frontier/results, declared target profile, exact `target_state`, Live Gate result, acceptance scope, every pending external confirmation, Context status and blockers. Use verifier terms exactly: `progress_passing` means targeted repair evidence, `progress_stale` is not a current pass, `final_workflow_status: null` means unfinished, `authority_revision_adopted` means return to rolling execution, and `machine_accepted_external_pending` must retain its named confirmations. Contract target states are only `implementation_complete`, `target_profile_usable` and `production_release_ready`; terminal failure uses `not_accepted` or `blocked_external`. Never shorten targeted progress to “Outcome complete” or invent per-platform progress/status. State the threat-model limits: undeclared requirements cannot be discovered, installed verifier/Git metadata are trusted, native-Goal/model selection belongs to the host/user, and internal platform delegation is not observed.

package/assets/skills/long-task-workflow/agents/openai.yaml

@@ -1,4 +1,4 @@
-interface:
-  display_name: "Long-Task Workflow"
-  short_description: "Run one Delivery Contract in the current native Goal"
-  default_prompt: "Use /long-task-workflow to prepare, execute, resume, verify, or close one Canonical Delivery Contract in the current workspace."
+interface:
+  display_name: "Long-Task Workflow"
+  short_description: "Run one Delivery Contract in the current native Goal"
+  default_prompt: "Use /long-task-workflow to prepare, execute, resume, verify, or close one Canonical Delivery Contract in the current workspace."

package/assets/skills/long-task-workflow/references/authority-lifecycle.md

@@ -1,59 +1,59 @@
-# Authority Lifecycle Reference
-
-Read this before Preflight, Compile, revision, resume, targeted verify, Final Gate, Stop, close or abandon.
-
-## Preflight And Compile
-
-Run `ty-context long-task preflight <workdir>` before first formal Compile. Resolve every `error` and `decision_required` diagnostic and review warnings. Preflight is read-only: it creates no Active Authority, initial base, marker, cache, Progress, Receipt or pending revision, runs no project Check and persists no success record.
-
-Preflight and Compile call the same activation-safety validator. Skipping Preflight bypasses no Source continuity, criterion, Claim/all-of-surface, Stage closure/cross-surface gate, required-target/root/runner binding, scenario/journey separation, capability adequacy, typed external impact, bounded Product Conformance, adapter/Observation, risk, owner/path/Binding, runner/input, Counterfactual or sensitivity rule.
-
-Preflight keeps every independently discovered diagnostic. When a structural duplicate makes the same Claim ambiguous or repeated, only that pair receives stable `diagnostic_id`, `repair_group`, `repair_priority` and `blocked_by` metadata so the structural blocker is repaired first. Independent findings keep their compact existing shape; no finding is hidden, reclassified or treated as resolved, and no repair state or authority is created.
-
-The first successful `ty-context long-task compile <workdir>` is Authority Lock and freezes the immutable initial base and complete compiled authority snapshot in Git common-dir, bound to the worktree marker by task id, revision and compiled identity.
-
-Its JSON result includes `execution_model_checkpoint.required: true`. Before product implementation, stop once and ask the user to continue with the current model or switch models and then resume the active Long-Task. A task-specific model choice already stated explicitly satisfies the checkpoint. Later Compile revisions return `required: false`; no checkpoint file, acknowledgement state, model route or automatic model switch is created.
-
-## Protected Revision
-
-After Authority Lock, every revision compares against active authority and follows one of three paths:
-
-1. proven monotonic evidence strengthening—including adding capabilities while preserving every existing Assertion meaning—pure verifier relocation, proven tightening and supporting-only Context revision may auto-revise;
-2. a candidate whose only protected reasons are owner, expected-change or allowed-support expansion remains inactive but may be exercised with `diagnose-revision` through existing active Check identities whose runner/verifier authority is unchanged; safe monotonic strengthening may coexist; or
-3. every Source/Product/target profile/required-target/Stage/success-degradation/external-impact semantic change, removed capability or scenario step, root-to-internal move, proof weakening, runner or verifier-content change, risk change or other protected reason requires the exact revision identity and is never candidate-executed.
-
-`diagnose-revision` recompiles the same `delivery-contract.yaml` in memory, creates only a disposable workspace snapshot when class 2 is proven, and returns transient repair results with `acceptance_authorized: false`. It writes no pending/approval state, authority/marker, cache, Progress or Receipt. Repeated edits therefore accumulate only in the one existing Contract authoring file, not a pending Draft authority or candidate state plane.
-
-Ordinary `compile --revise` is the only operation that may create the one pending decision. It binds a deterministic concise change summary into the revision identity and enumerates changed semantic fields, Source/Product Claim reductions, proof reductions and external-confirmation keys. `status` and `resume` expose that same decision so the host can deduplicate the user prompt without a Harness-owned waiting state. The executing Agent never approves its own pending revision; earlier blanket authorization cannot approve a later exact identity. If the candidate changes, the identity changes and old approval is rejected. The previous Authority remains active until approved compare-and-swap adoption. Adoption reports `delivery_completed_by_this_event: false`, invalidates affected evidence and returns to rolling implementation or repair under the revised Authority; the complete source-recompiled Final Gate remains mandatory.
-
-Every path-bearing field uses canonical grammar. Internal `.`/`..`, control characters, empty segments, absolute/drive/UNC paths and unsupported glob syntax fail closed.
-
+# Authority Lifecycle Reference
+
+Read this before Preflight, Compile, revision, resume, targeted verify, Final Gate, Stop, close or abandon.
+
+## Preflight And Compile
+
+Run `ty-context long-task preflight <workdir>` before first formal Compile. Resolve every `error` and `decision_required` diagnostic and review warnings. Preflight is read-only: it creates no Active Authority, initial base, marker, cache, Progress, Receipt or pending revision, runs no project Check and persists no success record.
+
+Preflight and Compile call the same activation-safety validator. Skipping Preflight bypasses no Source continuity, criterion, Claim/all-of-surface, Stage closure/cross-surface gate, required-target/root/runner binding, scenario/journey separation, capability adequacy, typed external impact, bounded Product Conformance, adapter/Observation, risk, owner/path/Binding, runner/input, Counterfactual or sensitivity rule.
+
+Preflight keeps every independently discovered diagnostic. When a structural duplicate makes the same Claim ambiguous or repeated, only that pair receives stable `diagnostic_id`, `repair_group`, `repair_priority` and `blocked_by` metadata so the structural blocker is repaired first. Independent findings keep their compact existing shape; no finding is hidden, reclassified or treated as resolved, and no repair state or authority is created.
+
+The first successful `ty-context long-task compile <workdir>` is Authority Lock and freezes the immutable initial base and complete compiled authority snapshot in Git common-dir, bound to the worktree marker by task id, revision and compiled identity.
+
+Its JSON result includes `execution_model_checkpoint.required: true`. Before product implementation, stop once and ask the user to continue with the current model or switch models and then resume the active Long-Task. A task-specific model choice already stated explicitly satisfies the checkpoint. Later Compile revisions return `required: false`; no checkpoint file, acknowledgement state, model route or automatic model switch is created.
+
+## Protected Revision
+
+After Authority Lock, every revision compares against active authority and follows one of three paths:
+
+1. proven monotonic evidence strengthening—including adding capabilities while preserving every existing Assertion meaning—pure verifier relocation, proven tightening and supporting-only Context revision may auto-revise;
+2. a candidate whose only protected reasons are owner, expected-change or allowed-support expansion remains inactive but may be exercised with `diagnose-revision` through existing active Check identities whose runner/verifier authority is unchanged; safe monotonic strengthening may coexist; or
+3. every Source/Product/target profile/required-target/Stage/success-degradation/external-impact semantic change, removed capability or scenario step, root-to-internal move, proof weakening, runner or verifier-content change, risk change or other protected reason requires the exact revision identity and is never candidate-executed.
+
+`diagnose-revision` recompiles the same `delivery-contract.yaml` in memory, creates only a disposable workspace snapshot when class 2 is proven, and returns transient repair results with `acceptance_authorized: false`. It writes no pending/approval state, authority/marker, cache, Progress or Receipt. Repeated edits therefore accumulate only in the one existing Contract authoring file, not a pending Draft authority or candidate state plane.
+
+Ordinary `compile --revise` is the only operation that may create the one pending decision. It binds a deterministic concise change summary into the revision identity and enumerates changed semantic fields, Source/Product Claim reductions, proof reductions and external-confirmation keys. `status` and `resume` expose that same decision so the host can deduplicate the user prompt without a Harness-owned waiting state. The executing Agent never approves its own pending revision; earlier blanket authorization cannot approve a later exact identity. If the candidate changes, the identity changes and old approval is rejected. The previous Authority remains active until approved compare-and-swap adoption. Adoption reports `delivery_completed_by_this_event: false`, invalidates affected evidence and returns to rolling implementation or repair under the revised Authority; the complete source-recompiled Final Gate remains mandatory.
+
+Every path-bearing field uses canonical grammar. Internal `.`/`..`, control characters, empty segments, absolute/drive/UNC paths and unsupported glob syntax fail closed.
+
 Controlling Context includes core Context, explicit `context_refs`, verification/deployment Context and every file in full snapshot mode. In referenced mode only graph-derived, non-explicit `implementation-index` and `archive` files are Supporting Context; a supporting-only `compile --revise` may preserve otherwise-fresh targeted Progress.
 
 A selected design target, its exact/constraint interpretation, an authored token source or any applicable Control semantic is product/verification authority, not generated evidence. External design resources are ordinary Source: a candidate or unresolved selection cannot authorize fidelity work, while a selected exact target still requires downstream UI Authority Closure and Contract adoption. Adding or changing its selected resource, selection basis, immutable identity, condition coverage or acceptance-affecting token/prototype fixture after Authority Lock follows the existing protected revision path and returns to rolling implementation; a candidate/planned target, implementation screenshot or historical diff cannot authorize fidelity work or preserve affected Progress by itself.
-
-`context.toml` retrieval guidance (`triggers`, `read_when`, `read_policy`, default selection and unselected nodes) is excluded from the selected delivery-authority projection. Selected area ownership, role/dependency structure and selected Context contents remain protected revision material. Retrieval-only edits may preserve scoped Progress, but a changed final Git tree still invalidates historical final acceptance and must pass the Live Final Gate again.
-
-## Targeted Verification And Recovery
-
-`verify --outcome/--check` runs scoped current-snapshot checks for repair and rechecks active identity before writing Progress. A Counterfactual finding is projected into the owning Main Check, changes an otherwise passed Check to `invalid_evidence`, clears Claim proofs and remains recoverable through `status`/`resume`. Global Checks use the same record without a new Global Outcome state.
-
-For a declared target-runtime Check, run targeted verify once when its earliest owning Outcome reaches the first runnable boundary. After accumulated changes to its declared `input_paths` or Binding carriers make Progress stale, rerun before dependent work grows. Coalesce related edits and use the cheapest reliable Check; do not create a per-edit/per-Outcome rebuild rule, trigger queue or platform state. These runs remain `acceptance_authorized: false`.
-
-Progress freshness binds Outcome authority, runner, verification inputs, Controlling Context and implementation inputs. Retry defaults to none; one retry is allowed only for explicit `transient_once`, idempotent, read-only/test-sandbox work.
-
-Status, Progress, Receipts and workdir compiled output are audit/recovery projections only. Development-period authority state is `manual_required` and never migrated.
-
-Report their exact meaning: `progress_passing` is current targeted repair evidence rather than “Outcome complete”; `progress_stale` is not a current pass; `final_workflow_status: null` means the Goal is unfinished. `status`/`resume` derive `ready_stages`, `ready_outcomes` and Stage status from current Progress; they do not persist a Stage pass. `target_state` remains `not_accepted` until a fresh Final Gate accepts, becomes `blocked_external` for a target blocker, or names the Contract's `implementation_complete`, `target_profile_usable` or `production_release_ready` state after machine acceptance. Do not invent per-platform progress/status.
-
-## Final Gate And Terminal Paths
-
-Before Final Gate, complete Context/code/tests and create a clean candidate commit. Final Gate captures active identity, recompiles Source authority, reads complete current Context, validates common-dir record/marker, creates a Git-tree snapshot, reruns all Checks and sensitivity controls and rechecks identity before acceptance. A target-runtime Check must exercise its exact target again in that Final Gate execution; rereading historical status does not become live proof merely because the reader reran. The Receipt reports the target profile/state and every Stage as `passed`, `failed`, `blocked_external` or `blocked_dependency`. A concurrent revision returns `active_authority_changed_during_final_gate`.
-
-Commit, verifier migration, clear and abandon share one active-state lock. Stop/close clear only the identity actually accepted through CAS and preserve `machine_accepted_external_pending` plus every named external confirmation in output. Final Gate/Stop/close identify `acceptance_scope: declared_machine_authority` and `native_goal_effect: none`; close additionally identifies `closed_scope: machine_authority`. The Stop Hook emits the same scope as one non-blocking message for either accepted machine status. A stale Receipt exposes no accepted workflow status.
-
-Before platform-native Goal completion, compare current Goal/user meaning with accepted marked Source and check for a pending revision, unresolved blocker or omitted requirement. This review may only veto completion and direct Source/Contract repair; it is not a second acceptance Gate and cannot create proof.
-
-For invalid, mismatched, unrecoverable or stale-lock continuity, use only `ty-context long-task abandon <workdir> --force-corrupt-state`; it preserves authored Contract, Source, Context and Git content.
-
-An older `long-task-delivery-v2` Contract that lacks Stage, required-target, scenario, journey, success/degradation, capability or typed external-impact fields is a manual migration. `upgrade --check` reports `long-task-v2-semantic-drift-authority`, and parsing lists missing field paths. Re-author those meanings from Source; never infer them from old Progress/Receipts or import historical passing evidence as acceptance.
+
+`context.toml` retrieval guidance (`triggers`, `read_when`, `read_policy`, default selection and unselected nodes) is excluded from the selected delivery-authority projection. Selected area ownership, role/dependency structure and selected Context contents remain protected revision material. Retrieval-only edits may preserve scoped Progress, but a changed final Git tree still invalidates historical final acceptance and must pass the Live Final Gate again.
+
+## Targeted Verification And Recovery
+
+`verify --outcome/--check` runs scoped current-snapshot checks for repair and rechecks active identity before writing Progress. A Counterfactual finding is projected into the owning Main Check, changes an otherwise passed Check to `invalid_evidence`, clears Claim proofs and remains recoverable through `status`/`resume`. Global Checks use the same record without a new Global Outcome state.
+
+For a declared target-runtime Check, run targeted verify once when its earliest owning Outcome reaches the first runnable boundary. After accumulated changes to its declared `input_paths` or Binding carriers make Progress stale, rerun before dependent work grows. Coalesce related edits and use the cheapest reliable Check; do not create a per-edit/per-Outcome rebuild rule, trigger queue or platform state. These runs remain `acceptance_authorized: false`.
+
+Progress freshness binds Outcome authority, runner, verification inputs, Controlling Context and implementation inputs. Retry defaults to none; one retry is allowed only for explicit `transient_once`, idempotent, read-only/test-sandbox work.
+
+Status, Progress, Receipts and workdir compiled output are audit/recovery projections only. Development-period authority state is `manual_required` and never migrated.
+
+Report their exact meaning: `progress_passing` is current targeted repair evidence rather than “Outcome complete”; `progress_stale` is not a current pass; `final_workflow_status: null` means the Goal is unfinished. `status`/`resume` derive `ready_stages`, `ready_outcomes` and Stage status from current Progress; they do not persist a Stage pass. `target_state` remains `not_accepted` until a fresh Final Gate accepts, becomes `blocked_external` for a target blocker, or names the Contract's `implementation_complete`, `target_profile_usable` or `production_release_ready` state after machine acceptance. Do not invent per-platform progress/status.
+
+## Final Gate And Terminal Paths
+
+Before Final Gate, complete Context/code/tests and create a clean candidate commit. Final Gate captures active identity, recompiles Source authority, reads complete current Context, validates common-dir record/marker, creates a Git-tree snapshot, reruns all Checks and sensitivity controls and rechecks identity before acceptance. A target-runtime Check must exercise its exact target again in that Final Gate execution; rereading historical status does not become live proof merely because the reader reran. The Receipt reports the target profile/state and every Stage as `passed`, `failed`, `blocked_external` or `blocked_dependency`. A concurrent revision returns `active_authority_changed_during_final_gate`.
+
+Commit, verifier migration, clear and abandon share one active-state lock. Stop/close clear only the identity actually accepted through CAS and preserve `machine_accepted_external_pending` plus every named external confirmation in output. Final Gate/Stop/close identify `acceptance_scope: declared_machine_authority` and `native_goal_effect: none`; close additionally identifies `closed_scope: machine_authority`. The Stop Hook emits the same scope as one non-blocking message for either accepted machine status. A stale Receipt exposes no accepted workflow status.
+
+Before platform-native Goal completion, compare current Goal/user meaning with accepted marked Source and check for a pending revision, unresolved blocker or omitted requirement. This review may only veto completion and direct Source/Contract repair; it is not a second acceptance Gate and cannot create proof.
+
+For invalid, mismatched, unrecoverable or stale-lock continuity, use only `ty-context long-task abandon <workdir> --force-corrupt-state`; it preserves authored Contract, Source, Context and Git content.
+
+An older `long-task-delivery-v2` Contract that lacks Stage, required-target, scenario, journey, success/degradation, capability or typed external-impact fields is a manual migration. `upgrade --check` reports `long-task-v2-semantic-drift-authority`, and parsing lists missing field paths. Re-author those meanings from Source; never infer them from old Progress/Receipts or import historical passing evidence as acceptance.

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

@@ -1,78 +1,78 @@
-# Contract Authoring Reference
-
-Read this only while authoring or structurally revising the one `delivery-contract.yaml` Draft.
-
-## Source And Semantic Boundary
-
-- Every declared Source file contains at least one Material Source Item. Mark items in original Markdown without rendering or changing meaning.
-- Marker keys and `source_claim` keys are set-equal and globally unique. `statement` preserves marked text after line-ending normalization, surrounding blank-line removal and trailing-space cleanup.
-- Typed dispositions keep Result, Requirement, Control, Technical Obligation, Non-completing Claim, Acceptance, Global Constraint/Non-goal, Forbidden Shortcut, Risk, External Confirmation and Decision distinct.
-- Every non-decision Source item owns exactly one same-kind, text-identical canonical target; no target may collapse multiple Source items. `out_of_scope` is not a resolution.
-- A Source AC maps criterion-identically to one named Assertion and proves at least one independently Source-backed non-Result Claim.
-- Missing recommended Source Plan headings or keys never blocks authoring. Missing mandatory Material Source Item markers does.
-- `delegated` in a Source Plan is provenance, not a Contract disposition or new Claim kind. An instruction to synthesize, refine, complete, implement or use judgment delegates plan-level authoring, but it does not invent material tradeoff preferences. Before comparative research or a material product, technical, architecture or provider selection, identify the criteria that could change the research scope, candidate set or recommendation. If such a preference is unknown or ambiguous, ask a concise targeted question before research or selection and keep the item `decision_required` until answered; do not impose a fixed questionnaire or re-ask preferences already supplied by the user, Source, Context or controlling constraints.
-- Once the material preference envelope is clear, use current authoritative or primary evidence for external capability, price, quota, license, compatibility, region, security posture or support claims. When one defensible recommendation exists, record the authoring instruction, preference/evidence or conservative-default basis and exact added meaning in real Source, then preserve that keyed item as ordinary Source of its semantic kind. If ordinary prose is the Source, append the delegated item without rewriting the user's original text; never place the choice only in Contract YAML.
-- A delegated plan choice is not action authorization. Payment, contracting, production deployment/publication, destructive production mutation, real permission grants, sensitive-data transmission and required legal/security/human approval remain named External Confirmations. Conflicting authority, an explicitly user-reserved choice, a missing material preference or the absence of a defensible recommendation remains `decision_required`; high impact or multiple options with known criteria alone does not.
-- A rolling implementation blocker is not an External Confirmation merely because work is difficult, delayed or unavailable through the current implementation path. Reclassify or remove machine-verifiable scope only through an explicit marked Source change and protected exact approval; otherwise keep the requirement and revise the implementation/evidence path.
-
-## Outcome Boundary
-
-Create an Outcome only when its result is independently observable, decidable, target-verifiable, dependency-expressible and localizable to its own Claims, Assertions, Checks and owner boundary. Requirement coupling, dependency-ready work, targeted verification, precise failure localization, semantic resume and stale-result invalidation are valid reasons to decompose. File count, implementation layer, context length, desired parallelism and Agent capacity are not.
-
-For every Outcome declare:
-
-- one complete observable result;
-- atomic requirements and actually applicable controls/states;
-- non-completing claims;
-- owner Context/surfaces and expected/support/forbidden path envelopes;
-- stable technical obligations, Bindings, forbidden shortcuts and recovery requirements;
-- risk facts;
-- executable Checks and named AC Assertions.
-
-Global non-goals, constraints and forbidden shortcuts remain Global authority and use Global Checks/Assertions when machine proof is required.
-
-## Stage And Target Profile
-
-- Declare one ordered `stages` DAG in the same Contract. Every Outcome belongs to exactly one Stage; every Stage names one gate Outcome; the gate transitively depends on every other Outcome in that Stage; and every later Stage Outcome transitively depends on every prerequisite gate.
-- A Stage Gate is not a second Final Gate or Receipt. It is one or more `stage_gate` Checks owned by the gate Outcome, and its status/frontier is derived from ordinary Outcome Progress.
-- A multi-Outcome Stage Gate declares `cross_surface_consistency`. Its runtime record names at least two distinct `surface_ref` values, may use the same runtime target for several pages, and proves one matching state version.
-- `task.target_profile` declares `required_state` plus a non-empty, duplicate-free `required_target_refs`. Each ref resolves to a `product` execution target with one bounded runtime family and root entrypoint. Every Stage Gate and every `critical_user_path` Outcome provides root `target_runtime` proof for every required ref; optional support/observer targets never substitute.
-- Use `implementation_complete` only when code-level implementation is the selected target, `target_profile_usable` when the declared required targets must be usable, and `production_release_ready` only when release gates are part of the selected target. These are terminal target qualifications, not Outcome progress states.
-
-## Architecture Closure
-
-Architecture protection is risk-triggered and project-specific. Use it when the delivery declares module ownership, unique source of truth, dependency direction, API/schema/data boundary, state lifecycle, persistence/recovery, security boundary, compatibility/migration or a forbidden bypass.
-
-Represent the invariant with existing Contract fields:
-
-1. a Source-backed technical obligation, global constraint or forbidden shortcut;
-2. owner Context and expected/support/forbidden paths;
-3. a Binding to the implementation carrier when Counterfactual sensitivity is required;
-4. a project-owned executable architecture check, such as the repository's lint, AST, dependency or contract test;
-5. a separate Assertion when functional behavior could pass while the architecture invariant fails.
-
-Do not encode subjective “clean architecture” or generic quality prose as machine authority. If no reliable observation can falsify it, keep it as durable Context/review judgment or return `decision_required`. Harness routes the repository's architecture check; it does not become a language-generic dependency analyzer.
-
-## Proxy And Target Runtime Independence
-
-When a declared result can pass on a proxy surface while failing in its target runtime, author independent target-runtime proof for the exact required target ref. Put the project-owned live Check in the earliest Outcome that owns the first runnable target boundary rather than postponing it to a terminal release/quality Outcome.
-
-Use existing Contract semantics:
-
-1. require `runtime_behavior` or the other proof surface that matches the actual Claim;
-2. make the accepting runner exercise the target during the current Raw Execution and derive its asserted Observation from that same session;
-3. include the runtime-affecting entrypoints, dependency manifests/lockfiles, configuration and integration carriers in `input_paths` or Bindings as appropriate;
-4. freeze runner helpers/configuration as `verification_inputs` and declare only genuine environment requirements; and
-5. add capability-specific probes only for Claims that actually require them.
-
-A proxy check, static repository shape, tracked status report, prior screenshot, binary or historical run cannot be the sole proof of a Claim that can fail independently in the target. Use only the bounded execution-target runtime families and required refs in the Contract; do not add open-ended `platform_impact` flags or per-platform Progress state.
-
-## Success, Degradation And External Boundaries
-
-- Set `success_path_required` and `degradation_path_required` explicitly. A Result Claim is proved only by a `success` Check; the same Check cannot be both success and degradation, and an honest unavailable/pending/recovery state cannot replace required success.
-- External confirmations declare `kind`, exact `impact_claims` and `blocks_target`. A `functional_prerequisite` blocks the selected target; a `production_release_gate` blocks a production-release target but may remain non-blocking for a lower target. Reclassification or impact changes are protected authority.
-- `boundary_invocation` and `external_side_effect` are machine evidence only when their Check executes on a declared independent `observer` target. Product self-report never proves the downstream effect.
-
+# Contract Authoring Reference
+
+Read this only while authoring or structurally revising the one `delivery-contract.yaml` Draft.
+
+## Source And Semantic Boundary
+
+- Every declared Source file contains at least one Material Source Item. Mark items in original Markdown without rendering or changing meaning.
+- Marker keys and `source_claim` keys are set-equal and globally unique. `statement` preserves marked text after line-ending normalization, surrounding blank-line removal and trailing-space cleanup.
+- Typed dispositions keep Result, Requirement, Control, Technical Obligation, Non-completing Claim, Acceptance, Global Constraint/Non-goal, Forbidden Shortcut, Risk, External Confirmation and Decision distinct.
+- Every non-decision Source item owns exactly one same-kind, text-identical canonical target; no target may collapse multiple Source items. `out_of_scope` is not a resolution.
+- A Source AC maps criterion-identically to one named Assertion and proves at least one independently Source-backed non-Result Claim.
+- Missing recommended Source Plan headings or keys never blocks authoring. Missing mandatory Material Source Item markers does.
+- `delegated` in a Source Plan is provenance, not a Contract disposition or new Claim kind. An instruction to synthesize, refine, complete, implement or use judgment delegates plan-level authoring, but it does not invent material tradeoff preferences. Before comparative research or a material product, technical, architecture or provider selection, identify the criteria that could change the research scope, candidate set or recommendation. If such a preference is unknown or ambiguous, ask a concise targeted question before research or selection and keep the item `decision_required` until answered; do not impose a fixed questionnaire or re-ask preferences already supplied by the user, Source, Context or controlling constraints.
+- Once the material preference envelope is clear, use current authoritative or primary evidence for external capability, price, quota, license, compatibility, region, security posture or support claims. When one defensible recommendation exists, record the authoring instruction, preference/evidence or conservative-default basis and exact added meaning in real Source, then preserve that keyed item as ordinary Source of its semantic kind. If ordinary prose is the Source, append the delegated item without rewriting the user's original text; never place the choice only in Contract YAML.
+- A delegated plan choice is not action authorization. Payment, contracting, production deployment/publication, destructive production mutation, real permission grants, sensitive-data transmission and required legal/security/human approval remain named External Confirmations. Conflicting authority, an explicitly user-reserved choice, a missing material preference or the absence of a defensible recommendation remains `decision_required`; high impact or multiple options with known criteria alone does not.
+- A rolling implementation blocker is not an External Confirmation merely because work is difficult, delayed or unavailable through the current implementation path. Reclassify or remove machine-verifiable scope only through an explicit marked Source change and protected exact approval; otherwise keep the requirement and revise the implementation/evidence path.
+
+## Outcome Boundary
+
+Create an Outcome only when its result is independently observable, decidable, target-verifiable, dependency-expressible and localizable to its own Claims, Assertions, Checks and owner boundary. Requirement coupling, dependency-ready work, targeted verification, precise failure localization, semantic resume and stale-result invalidation are valid reasons to decompose. File count, implementation layer, context length, desired parallelism and Agent capacity are not.
+
+For every Outcome declare:
+
+- one complete observable result;
+- atomic requirements and actually applicable controls/states;
+- non-completing claims;
+- owner Context/surfaces and expected/support/forbidden path envelopes;
+- stable technical obligations, Bindings, forbidden shortcuts and recovery requirements;
+- risk facts;
+- executable Checks and named AC Assertions.
+
+Global non-goals, constraints and forbidden shortcuts remain Global authority and use Global Checks/Assertions when machine proof is required.
+
+## Stage And Target Profile
+
+- Declare one ordered `stages` DAG in the same Contract. Every Outcome belongs to exactly one Stage; every Stage names one gate Outcome; the gate transitively depends on every other Outcome in that Stage; and every later Stage Outcome transitively depends on every prerequisite gate.
+- A Stage Gate is not a second Final Gate or Receipt. It is one or more `stage_gate` Checks owned by the gate Outcome, and its status/frontier is derived from ordinary Outcome Progress.
+- A multi-Outcome Stage Gate declares `cross_surface_consistency`. Its runtime record names at least two distinct `surface_ref` values, may use the same runtime target for several pages, and proves one matching state version.
+- `task.target_profile` declares `required_state` plus a non-empty, duplicate-free `required_target_refs`. Each ref resolves to a `product` execution target with one bounded runtime family and root entrypoint. Every Stage Gate and every `critical_user_path` Outcome provides root `target_runtime` proof for every required ref; optional support/observer targets never substitute.
+- Use `implementation_complete` only when code-level implementation is the selected target, `target_profile_usable` when the declared required targets must be usable, and `production_release_ready` only when release gates are part of the selected target. These are terminal target qualifications, not Outcome progress states.
+
+## Architecture Closure
+
+Architecture protection is risk-triggered and project-specific. Use it when the delivery declares module ownership, unique source of truth, dependency direction, API/schema/data boundary, state lifecycle, persistence/recovery, security boundary, compatibility/migration or a forbidden bypass.
+
+Represent the invariant with existing Contract fields:
+
+1. a Source-backed technical obligation, global constraint or forbidden shortcut;
+2. owner Context and expected/support/forbidden paths;
+3. a Binding to the implementation carrier when Counterfactual sensitivity is required;
+4. a project-owned executable architecture check, such as the repository's lint, AST, dependency or contract test;
+5. a separate Assertion when functional behavior could pass while the architecture invariant fails.
+
+Do not encode subjective “clean architecture” or generic quality prose as machine authority. If no reliable observation can falsify it, keep it as durable Context/review judgment or return `decision_required`. Harness routes the repository's architecture check; it does not become a language-generic dependency analyzer.
+
+## Proxy And Target Runtime Independence
+
+When a declared result can pass on a proxy surface while failing in its target runtime, author independent target-runtime proof for the exact required target ref. Put the project-owned live Check in the earliest Outcome that owns the first runnable target boundary rather than postponing it to a terminal release/quality Outcome.
+
+Use existing Contract semantics:
+
+1. require `runtime_behavior` or the other proof surface that matches the actual Claim;
+2. make the accepting runner exercise the target during the current Raw Execution and derive its asserted Observation from that same session;
+3. include the runtime-affecting entrypoints, dependency manifests/lockfiles, configuration and integration carriers in `input_paths` or Bindings as appropriate;
+4. freeze runner helpers/configuration as `verification_inputs` and declare only genuine environment requirements; and
+5. add capability-specific probes only for Claims that actually require them.
+
+A proxy check, static repository shape, tracked status report, prior screenshot, binary or historical run cannot be the sole proof of a Claim that can fail independently in the target. Use only the bounded execution-target runtime families and required refs in the Contract; do not add open-ended `platform_impact` flags or per-platform Progress state.
+
+## Success, Degradation And External Boundaries
+
+- Set `success_path_required` and `degradation_path_required` explicitly. A Result Claim is proved only by a `success` Check; the same Check cannot be both success and degradation, and an honest unavailable/pending/recovery state cannot replace required success.
+- External confirmations declare `kind`, exact `impact_claims` and `blocks_target`. A `functional_prerequisite` blocks the selected target; a `production_release_gate` blocks a production-release target but may remain non-blocking for a lower target. Reclassification or impact changes are protected authority.
+- `boundary_invocation` and `external_side_effect` are machine evidence only when their Check executes on a declared independent `observer` target. Product self-report never proves the downstream effect.
+
 ## Visual Delivery Authoring
 
 When the selected delivery includes a new/redesigned screen, primary layout/navigation/theme/component system, high-fidelity implementation or other material production UI, resolve Design Authority before Compile and author the result through existing Contract semantics:
@@ -80,23 +80,23 @@ When the selected delivery includes a new/redesigned screen, primary layout/navi
 - when external design resources are material Source, place stable authored files or an accompanying controlling brief/index in `source_paths`, enumerate material statements with ordinary Source markers and preserve stable surface/state/control/target keys where available. Treat candidates and unresolved decisions honestly; only a selected exact target with a valid selection basis, declared condition coverage and immutable identity can be proposed for fidelity authority, and downstream UI Authority Closure still owns adoption;
 - perform UI Authority Closure over stable surface/control/target keys: classify each material item as covered by owning Context/`DESIGN.md`, requiring an owner update, task-local Source, explicitly out of scope or genuinely `decision_required`. Product Surface Context owns cross-surface responsibility, Screen/interaction Context owns durable hierarchy/behavior, `DESIGN.md` owns visual-system/reference semantics and selected targets own concrete composition; Contract YAML must not duplicate or invent those owners;
 - inspect owning surface/interaction Context, `DESIGN.md`, its authored token source/generation direction and material design references. Classify every reference as `exact-target`, `constraint` or `inspiration`, with its surface/route/component, path/URI and covered viewport/theme/mode/state;
-- an unconfigured starter, style-only prose, inspiration-only set or conflicting target is not sufficient production authority. Resolve it by explicitly scoping Source to a prototype/non-fidelity result, recording an explicitly delegated and selected design target in real Source after material preferences are known, or keeping the unresolved/user-reserved direction `decision_required`;
-- never let implementation output authorize itself: a generated implementation screenshot/diff is an Artifact, not the target. An acceptance-affecting target or baseline must be selected Source/verifier input before fidelity implementation can be accepted;
-- derive a task-local, risk-proportional Visual Coverage Set from declared Source, `project_context/**` and `DESIGN.md`: production surface/route/component, viewport, theme or product mode, interaction/state, content stress and accessibility/motion conditions;
-- select representative combinations rather than silently creating a full Cartesian requirement; an omitted combination remains unproven, while Source that explicitly requires full coverage must retain that scope;
+- an unconfigured starter, style-only prose, inspiration-only set or conflicting target is not sufficient production authority. Resolve it by explicitly scoping Source to a prototype/non-fidelity result, recording an explicitly delegated and selected design target in real Source after material preferences are known, or keeping the unresolved/user-reserved direction `decision_required`;
+- never let implementation output authorize itself: a generated implementation screenshot/diff is an Artifact, not the target. An acceptance-affecting target or baseline must be selected Source/verifier input before fidelity implementation can be accepted;
+- derive a task-local, risk-proportional Visual Coverage Set from declared Source, `project_context/**` and `DESIGN.md`: production surface/route/component, viewport, theme or product mode, interaction/state, content stress and accessibility/motion conditions;
+- select representative combinations rather than silently creating a full Cartesian requirement; an omitted combination remains unproven, while Source that explicitly requires full coverage must retain that scope;
 - encode each independently falsifiable visual expectation as an atomic Requirement, applicable Control field or named AC Assertion. Name the surface, viewport, theme/state/content condition and observable result when they matter to the claim;
 - preserve every applicable material Control field independently: `surface`, `region`, `location`, `control_type`, `label_content`, `user_task`, `visibility`, `availability`, `trigger`, `input`, `validation`, `default_value`, `interaction`, `navigation_result`, `loading_state`, `empty_state`, `success_state`, `failure_state`, `recovery`, `permission`, `feedback` and `accessibility`. Empty/non-applicable fields create no Claim; do not collapse decided fields into broad prose that loses Source-to-Control traceability;
 - bind the declared result to the owning Context/`DESIGN.md`, one authored token source and generation direction, selected target/constraint inputs, production component/route carriers, path envelopes and project-owned target checks. Freeze acceptance-affecting selected target files, token sources and fixed prototype fixtures in `verification_inputs`; bind production carriers through `input_paths`/Bindings and reserve `artifact_globs` for generated implementation renders, diffs and reports. Detached kits, mocks or marketing specimens may be references but not substitute implementation carriers;
-- use `ui_browser` only for declared browser ACs. A browser or Expo-Web proxy cannot prove a native/mobile/desktop target that can fail independently; use a project-owned current-execution target Check when existing proof surfaces can truthfully represent the claim, otherwise retain named human/device confirmation as an external confirmation rather than inventing machine proof;
+- use `ui_browser` only for declared browser ACs. A browser or Expo-Web proxy cannot prove a native/mobile/desktop target that can fail independently; use a project-owned current-execution target Check when existing proof surfaces can truthfully represent the claim, otherwise retain named human/device confirmation as an external confirmation rather than inventing machine proof;
 - keep subjective visual direction, taste or approval outside false machine proof. Resolve an undecided direction as `decision_required`; represent required human design or new-baseline approval as an explicit external confirmation.
 - for combined design-and-implementation delivery, ordinary design Outcomes/Stages may author candidates before selection, but candidate/planned artifacts cannot authorize fidelity Claims. Append the selected result to real marked Source and the owning registry/target input; after Authority Lock adopt it through the existing protected revision before downstream fidelity implementation. This creates no target-selection state, second Contract or second Gate.
 
 External authored design resources remain ordinary upstream Source rather than a Contract Draft, verification result or alternate authority. This guidance adds no UI-specific Contract block, Claim kind, risk level, lifecycle state, required design package, design directory or Gate. The additive generic Control fields only preserve Source meaning through existing Source, Requirement/Control/Assertion, Stage, Binding, proof-surface, verification-input, revision and external-confirmation mechanisms.
-
-## Compact Authoring
-
-Compact V2 may omit only deterministic defaults: empty optional arrays/nulls, `context_snapshot_mode: referenced`, `requested_level: auto`, runner `argv: []`, `cwd: .`, `timeout_ms: 30000`, `retry_policy: none`, `idempotent: false`, and empty output/artifact/assertion/environment lists.
-
-Goal, target profile/required targets, ordered Stages, Source/Source Claims, Context, observable results, success/degradation requirements, owners/paths, REQ, applicable CTRL states, OBL, proof surfaces, Given/When scenarios, journey roles, Evidence Capabilities, runner targets/effects, verification inputs, Assertions, risk, forbidden shortcuts and typed external confirmations remain explicit.
-
-Compiler-generated Outcome/Check/Claim identities replace handwritten mechanical cross-entity references. This does not authorize compiler inference of product meaning, owners, architecture, proof or risk.
+
+## Compact Authoring
+
+Compact V2 may omit only deterministic defaults: empty optional arrays/nulls, `context_snapshot_mode: referenced`, `requested_level: auto`, runner `argv: []`, `cwd: .`, `timeout_ms: 30000`, `retry_policy: none`, `idempotent: false`, and empty output/artifact/assertion/environment lists.
+
+Goal, target profile/required targets, ordered Stages, Source/Source Claims, Context, observable results, success/degradation requirements, owners/paths, REQ, applicable CTRL states, OBL, proof surfaces, Given/When scenarios, journey roles, Evidence Capabilities, runner targets/effects, verification inputs, Assertions, risk, forbidden shortcuts and typed external confirmations remain explicit.
+
+Compiler-generated Outcome/Check/Claim identities replace handwritten mechanical cross-entity references. This does not authorize compiler inference of product meaning, owners, architecture, proof or risk.