dev-flow-deepseek 0.8.7 → 0.8.9

package/skills/dev-flow/references/method-profiles.md

@@ -75,18 +75,19 @@ only when actually visible and appropriate to the current authorized artifacts.
 | `tasks.decompose` | Decompose the current design into bounded, ordered work items. | Create bounded items with dependencies and expected paths. | `speckit-tasks`. | Revise proposal task artifacts through visible `openspec-propose`. | Current bounded task plan. |
 | `tasks.map_acceptance` | Map every current acceptance criterion to work and verification. | Record acceptance-to-work and verification traceability. | `speckit-tasks`. | Review delta specifications and tasks through visible `openspec-propose`. | Acceptance traceability. |
 | `tasks.analyze_consistency` | Check requirements, design, and tasks for gaps or contradictions. | Perform a direct cross-artifact consistency review. | `speckit-analyze`. | `openspec-validate` plus direct consistency review. | No unresolved blocking consistency gap, or exact findings. |
+| `tasks.plan_verification` | Set initial verification effort after scope, impact, work, and existing tests are understood. | Record intended checks and rationales, expected automatic commands, full-suite expectation, and test-code expectation. | Direct Task Plan work after `speckit-tasks`; no separate capability. | Revise proposal task artifacts through visible `openspec-propose`. | Current `verification_plan` inside the Task Plan baseline. |
 | `implementation.execute_plan` | Execute only the work authorized by the current task plan. | Implement the current authorized slice. | `speckit-implement`. | `openspec-apply`. | Implemented current work slice. |
-| `implementation.record_surface` | Record exact changed paths or the no-change state and deviations. | Observe and record the exact changed surface. | Direct implementation result; no mandatory capability. | Direct apply result; no mandatory capability. | Changed paths or explicit no-change result. |
+| `implementation.record_surface` | Reconcile the implementation summary with Core's observed Task surface. | Review the actual worktree state and summarize deviations; Core computes paths. | Direct implementation result; no mandatory capability. | Direct apply result; no mandatory capability. | Implementation summary aligned with the observed Task surface. |
 | `implementation.classify_deviations` | Classify deviations as requirement, design, or complexity concerns. | Record the exact concern and route it through Core facts. | Direct classification; amend active artifacts before continuing when semantics change. | Direct classification and current change-artifact update. | Exact deviations and findings. |
-| `test.run_budgeted_checks` | Run only verification authorized by the current verification budget. | Run the current bounded verification steps. | Direct plan-defined checks; no mandatory Spec Kit capability. | Use `openspec-verify` only when visible; otherwise run plan-defined checks. | Actual current verification result. |
-| `test.record_evidence` | Record actual evidence sources, outcomes, and unverified or manual items. | Record actual sources and statuses without relabeling; report only file changes newly produced by this TEST Action. Verification-only work uses `changed_paths=[]` and `no_file_changes=true`. | Direct evidence recording; no mandatory capability. | Direct evidence recording; no mandatory capability. | Current bounded evidence summary. |
+| `test.run_budgeted_checks` | Choose the closest necessary checks and adjust insufficient capacity before extra commands run. | Recheck scope before every command; use a justified TEST self-transition before exceeding budget and reassess every full suite. | Direct plan-defined checks; no mandatory Spec Kit capability. | Use `openspec-verify` only when visible and justified; otherwise run plan-defined checks. | Actual bounded result or a recorded pre-run budget increase. |
+| `test.record_evidence` | Record actual evidence or the exact pre-run budget adjustment. | Record actual sources and statuses; full suites include the current reason, while an adjustment records its basis, checks, increment, and reason. | Direct evidence recording; no mandatory capability. | Direct evidence recording; no mandatory capability. | Current evidence summary or budget-adjustment record. |
 | `test.classify_failure` | Classify failures as implementation, design, or requirement problems. | Classify current failures from observed facts. | Direct classification; no mandatory capability. | Direct classification; no mandatory capability. | Exact failure class and findings. |
 | `comprehension.explain` | Explain current behavior, design, and code paths in developer-readable terms. | Present a bounded explanation to the developer. | Direct review; no Spec Kit command owns the verdict. | Direct review; no OpenSpec command owns the verdict. | Developer-readable explanation. |
 | `comprehension.identify_complexity` | Identify unnecessary abstractions and maintenance risks. | List concrete complexity and maintenance concerns. | Direct review; no mandatory capability. | Direct review; no mandatory capability. | Exact abstraction and risk findings. |
 | `comprehension.obtain_user_verdict` | Obtain the developer's explicit understanding or remediation verdict. | Ask the developer and wait for an explicit answer. | Direct user interaction; no Spec Kit capability can answer. | Direct user interaction; no OpenSpec capability can answer. | Explicit current user verdict. |
 | `refactor.simplify` | Remove unnecessary complexity within the approved behavior boundary. | Perform the bounded simplification. | `speckit-implement` only after affected artifacts and tasks are current. | Update change artifacts as needed, then use visible `openspec-apply`. | Bounded simplification. |
 | `refactor.reconcile_artifacts` | Reconcile affected process artifacts with the simplification. | Amend only artifacts affected by the simplification. | Use visible `speckit-clarify`, `speckit-plan`, `speckit-tasks`, or `speckit-analyze` only as needed. | Revise proposal/design/spec/task artifacts through visible `openspec-propose` as needed. | Current affected artifacts. |
-| `refactor.record_surface` | Record exact simplifications and the changed surface. | Record simplifications and exact changed paths. | Direct refactor result; no mandatory capability. | Direct apply result; no mandatory capability. | Refactor summary and changed surface. |
+| `refactor.record_surface` | Reconcile simplifications with Core's observed Task surface. | Record simplifications and deviations; Core computes paths. | Direct refactor result; no mandatory capability. | Direct apply result; no mandatory capability. | Refactor summary aligned with the observed Task surface. |
 | `delivery.reconcile_acceptance` | Map the latest acceptance criteria to current test and comprehension evidence. | Reconcile every current criterion with current evidence. | `speckit-analyze` or direct final consistency review. | Use visible `openspec-verify` and/or `openspec-validate` as appropriate. | Current acceptance/evidence mapping. |
 | `delivery.reconcile_method_artifacts` | Reconcile method artifacts with delivered behavior. | Ensure current process artifacts describe the delivered behavior. | Direct status reconciliation; `speckit-converge` may be used only when available and appropriate. | Use visible `openspec-sync` and/or `openspec-archive` only when appropriate. | Current reconciled or archived change artifacts. |
 | `delivery.prepare_summary` | Prepare a bounded delivery summary and remaining risks. | Write the final bounded summary and risks. | Direct summary; no mandatory capability. | Direct summary; no mandatory capability. | Delivery summary and remaining risks. |

package/skills/dev-flow/references/node-payloads.md

@@ -47,33 +47,48 @@ For a file-scope blocker, `dev_flow_resolve_blocker` also requires `choice` (`al
 `expand_scope`, or `reject`) and a non-empty `reason`. Omit both members for repository-recovery and
 automatic-verification blockers.
 
+For `task_relocation_pending`, provide the retained `relocation_id` and every
+`relocation_destinations[{key,repository_path}]`. For `workspace_history_conflict`, provide
+`history_resolution` with exactly `choice="accept_current_history"` and a non-empty `reason` after
+explicit review. File-scope, relocation, and history members are mutually exclusive; use only the
+branch selected by the current blocker and live schema.
+
 ## Node-result members
 
 Use the live tool schema for types and nested members. These are the closed top-level members:
 
 | Submission tool | Required `node_result` members |
 | --- | --- |
-| Requirements | `problem_class`, `baseline`, `unresolved_questions`, `changed_paths`, `no_file_changes` |
-| Design | `problem_class`, `baseline`, `findings`, `changed_paths`, `no_file_changes` |
-| Tasks | `problem_class`, `baseline`, `findings`, `changed_paths`, `no_file_changes` |
-| Implementation | `problem_class`, `completed_work_item_ids`, `changed_paths`, `no_file_changes`, `deviations`, `findings` |
-| Test | `problem_class`, `checks`, `failed_items`, `unverified_items`, `manual_handoff_items`, `findings`, `changed_paths`, `no_file_changes` |
-| Comprehension | `problem_class`, `explained_components`, `unresolved_questions`, `unnecessary_abstractions`, `maintenance_risks`, `user_confirmation`, `findings`, `changed_paths`, `no_file_changes` |
-| Refactor | `problem_class`, `changed_paths`, `no_file_changes`, `simplifications`, `behavior_change_intended`, `findings` |
-| Delivery | `problem_class`, `unverified_items`, `risks`, `findings`, `changed_paths`, `no_file_changes` |
-
-`changed_paths` and `no_file_changes` remain mutually exclusive. A single-repository Task uses
-repository-relative paths. A multi-repository Task uses
-`<repository-key>::<repository-relative-path>`. Contract paths use `/` separators on every Host;
-backslashes are invalid even on Windows.
+| Requirements | `problem_class`, `baseline`, `unresolved_questions` |
+| Design | `problem_class`, `baseline`, `findings` |
+| Tasks | `problem_class`, `baseline`, `findings` |
+| Implementation | `problem_class`, `completed_work_item_ids`, `deviations`, `findings` |
+| Test | `problem_class`, `checks`, `failed_items`, `unverified_items`, `manual_handoff_items`, `findings`, `budget_adjustment` |
+| Comprehension | `problem_class`, `explained_components`, `unresolved_questions`, `unnecessary_abstractions`, `maintenance_risks`, `user_confirmation`, `findings` |
+| Refactor | `problem_class`, `simplifications`, `behavior_change_intended`, `findings` |
+| Delivery | `problem_class`, `unverified_items`, `risks`, `findings` |
+
+The Host never submits file-effect fields. Core observes the dedicated worktree before applying an
+Action and computes the Action delta and current Task surface from Git facts.
 
 Delivery submissions never send `acceptance`, `automated_evidence_ids`, `manual_evidence_ids`,
 `test_record_id`, or `comprehension_record_id`. Core derives those authority members from the current
 Requirements, Test, Comprehension, and Evidence records before canonical validation and Recovery
 retention. A submission containing any of those members violates the closed contract.
 
-Completed developer-run verification is a `source="user"` check with `command_count=0` and
-`full_suite=false`. Put only work nobody has run yet in `manual_handoff_items`.
+The Tasks baseline contains `work_items` plus `verification_plan`. The plan contains `checks[]` with
+`name` and `rationale`, `initial_budget`, `full_suite_expected`, and
+`test_code_changes_expected`. Core fills only `design_revision`.
+
+Every Test submission includes `budget_adjustment`. Normal pass/failure transitions send `null`.
+`verification_budget_increased` sends a closed adjustment with `basis`, `additional_checks`,
+`additional_automatic_commands`, `allow_full_suite`, and `allow_manual_handoff`; all check and result
+lists stay empty and the transition reason gives the concrete need. Every check includes
+`full_suite_reason`: it is empty unless `full_suite=true`, in which case it records the current
+suite-specific risk.
+
+Completed developer-run verification is a `source="user"` check with `command_count=0`,
+`full_suite=false`, and `full_suite_reason=""`. Put only work nobody has run yet in `manual_handoff_items`.
 
 ## Requirements example
 
@@ -104,9 +119,7 @@ Completed developer-run verification is a `source="user"` check with `command_co
       "constraints": [],
       "assumptions": []
     },
-    "unresolved_questions": [],
-    "changed_paths": [],
-    "no_file_changes": true
+    "unresolved_questions": []
   }
 }
 ```