@danmoisan/drm-copilot-mcp 1.1.16 → 1.1.17

package/resources/customizations/.github/agents/python-orchestrator.agent.md

@@ -97,7 +97,7 @@ Use these reusable skills to avoid duplicating shared operations:
 3) **Single source of routing truth = change budget**
 - First action is always to estimate rough change budget by identifying likely affected production Python files.
 - If estimate is `1-3` production Python files (+ corresponding tests), use **small path**.
-- If estimate is `>3` production Python files or `>3` test Python files, use **large path**.
+- If estimate is more than 3 (`>3`) production Python files, use **large path**. The large path has no production-file cap. Test files are not counted toward the routing threshold.
 
 4) **Deterministic variable handling**
 - Persist and reuse these variables exactly as names:
@@ -117,7 +117,7 @@ Use these reusable skills to avoid duplicating shared operations:
 
 ## Phase 0 — Intake and budget estimate (mandatory)
 
-1. Read user request and infer likely touched production Python files and/or test Python files.
+1. Read user request and infer likely touched production Python files.
 2. Estimate rough change budget.
 3. Write/update orchestration checkpoint.
 4. Route to one of two paths:
@@ -126,7 +126,7 @@ Use these reusable skills to avoid duplicating shared operations:
 
 ---
 
-## Small path (budget 1-3 production Python files and 1-3 test Python files)
+## Small path (budget 1-3 production Python files)
 
 Follow this exact sequence.
 
@@ -243,7 +243,7 @@ Hard enforcement for S8:
 
 ---
 
-## Large path (budget >3 production Python files or >3 test Python files)
+## Large path (budget >3 production Python files)
 
 Follow this exact sequence.
 

package/resources/customizations/.github/agents/python-typed-engineer.agent.md

@@ -58,12 +58,12 @@ If any instructions conflict, **halt and notify the user**.
 
 ## 1) Scope control (NO scope creep)
 
-- Default scope is **one feature slice** (typically **1–3 production files** within the same package) plus its corresponding test file(s).
-- You may touch up to **3 production files** without additional approval **only** when it is required to:
+- Default scope is **one feature slice** (typically **1-3 production files** within the same package) plus its corresponding test file(s).
+- Within the direct-mode budget, a slice may include production files beyond the primary module only when it is required to:
   - introduce a minimal seam for testability (I/O boundary isolation, dependency injection),
   - make typing changes required for Pyright cleanliness in the slice, or
   - update the smallest set of call sites needed to preserve a stable public API.
-- Any change beyond **3 production files** requires explicit user approval.
+- If the change requires more than 3 production files, stop and instruct the caller to use `python-orchestrator` (or `.github/prompts/orchestrate-python-work.prompt.md`). The orchestrated large path has no production-file cap.
 - You may not modify additional production files unless:
   - the user explicitly expands scope, OR
   - a shared helper is objectively broken and the minimal fix is required for the in-scope change.
@@ -73,11 +73,10 @@ If any instructions conflict, **halt and notify the user**.
   - the smallest alternative that avoids expanding scope
   Proceed only after user approval.
 
-## 2) Change budget (hard gate)
+## 2) Change budget (routing threshold)
 
-- Per batch you may change at most **3 production files** and **3 test files**. This is the default and the hard gate. A user-supplied override may be honored only if it complies with repo policy and approved scope; if the requested scope exceeds 3 production files overall, stop before execution and seek explicit approval.
-- Override by specifying ‘budget: prod=<N>, test=<M>’ in the user prompt before Phase C begins.
-- If no override is provided, the 3/3 limit applies; if an override is requested, comfirm compliance before Phase C. 
+- Direct mode budget: 1-3 production Python files (+ corresponding tests). A change of more than 3 production Python files belongs on the orchestrated large path (`python-orchestrator`).
+- Test files are not counted toward the routing threshold, and the orchestrated large path has no production-file cap.
 
 ## 3) Deterministic unit tests only (no temp files, no external systems)
 
@@ -135,7 +134,7 @@ If no plan is provided, delegate the creation of a plan to the `atomic_planner`.
 - Mocking plan (what is mocked, where patched, and why)
 - Exact files to change (must match scope guardrails)
 
-Before exiting Phase B, perform a quick line-count check on all in-scope files. If any file is near the 500-line limit or planned additions would push it over 500, decide upfront to split now (counting new files against the budget) or seek an override before Phase C. If uncertain, treat it as at-risk and plan for a split rather than discovering it mid-execution. If an approved plan would create a 500-line violation, halt and seek clarification before proceeding.
+Before exiting Phase B, perform a quick line-count check on all in-scope files. If any file is near the 500-line limit or planned additions would push it over 500, decide upfront to split now (counting new files against the budget) before Phase C. If uncertain, treat it as at-risk and plan for a split rather than discovering it mid-execution. If an approved plan would create a 500-line violation, halt and seek clarification before proceeding.
 
 Do not proceed to edits until the user explicitly approves (e.g., “Proceed.”).
 However, if a plan is provided in the initial prompt, it is already implicitly approved.

package/resources/customizations/.github/prompts/orchestrate-python-work.prompt.md

@@ -20,10 +20,10 @@ Coordinate the user request from intake to completion using the correct path bas
 
 ## Required orchestration behavior
 
-1. Estimate rough change budget first (production Python files and test Python files).
-2. If budget is **1–3 production Python files** (+ corresponding tests):
+1. Estimate rough change budget first (production Python files; test files are not counted toward the routing threshold).
+2. If budget is **1-3 production Python files** (+ corresponding tests):
    - Delegate directly to `python-typed-engineer` for plan + implementation + QA closure.
-3. If budget is **>3 production Python files** or **>3 test Python files**:
+3. If budget is **more than 3 production Python files**:
    - Execute full large-path lifecycle:
      1) Scope and create potential entry (`feature` vs `bug`, short-name creation)
      2) Promote to GitHub issue and capture issue metadata

package/resources/powershell/PoshQC/settings/pester.runsettings.psd1

@@ -29,7 +29,7 @@
             '.claude/hooks/check-powershell-test-purity.ps1'
             '.claude/hooks/enforce-python-batch-budget.ps1'
             '.claude/hooks/enforce-powershell-batch-budget.ps1'
-            '.claude/hooks/enforce-powershell-batch-budget-route.ps1'
+            '.claude/hooks/enforce-batch-budget-route.ps1'
             # Issue #272 hardened this PreToolUse hook with a new orchestrator-state preflight
             # check; measured here so the change produces real per-file coverage evidence.
             '.claude/hooks/enforce-pr-author-skill.ps1'
@@ -45,8 +45,10 @@
             '.claude/hooks/enforce-epic-merge-gate.ps1'
             # Issue #670: CodeCoverage.Path is an explicit per-file allow-list, so the dot-sourced helpers file is listed here.
             '.claude/hooks/enforce-epic-merge-gate-authorization.ps1'
+            '.claude/hooks/enforce-epic-merge-gate-resolution.ps1'
             '.claude/hooks/enforce-epic-wave-barrier.ps1'
             '.claude/hooks/enforce-epic-worktree-removal-gate.ps1'
+            '.claude/hooks/enforce-epic-worktree-removal-gate-resolution.ps1'
             '.claude/hooks/enforce-pr-author-skill.ps1'
             '.claude/hooks/validate-orchestrator-output.ps1'
             '.claude/hooks/enforce-pr-author-skill.epic-base-branch.ps1'
@@ -135,6 +137,7 @@
             '.codex/hooks/check-powershell-test-purity.ps1'
             '.codex/hooks/enforce-python-batch-budget.ps1'
             '.codex/hooks/enforce-powershell-batch-budget.ps1'
+            '.codex/hooks/enforce-batch-budget-route.ps1'
             '.codex/hooks/enforce-evidence-locations.ps1'
             '.codex/hooks/enforce-checkpoint-monotonic.ps1'
             '.codex/hooks/enforce-orchestration-preimplementation-gate.ps1'
@@ -318,11 +321,19 @@
             # Issue #663 added the epic-scope resolver and its pure readiness predicates.
             '.claude/lib/worktree-resolution/EpicScopeResolution.psm1'
             '.claude/lib/worktree-resolution/EpicScopeReadiness.psm1'
+            # Issue #690 added the run-target resolver; registered so it stays in the coverage denominator.
+            '.claude/lib/worktree-resolution/WorktreeRunResolution.psm1'
             # Issue #762 relocated the CI gate parser into the bundled .claude/lib tree so
             # push-down carries it with the orchestrate and epic-orchestrate skills.
             # CodeCoverage.Path is an explicit per-file allow-list, so the relocated production
             # file is registered here to stay in the coverage denominator.
             '.claude/lib/ci-gate/Invoke-CiGateParser.ps1'
+            # Issue #763 ported radius drift detection to the destination runtime as two pure
+            # modules and an entry script under .claude/lib/parallel-drift. CodeCoverage.Path is an
+            # explicit per-file allow-list, so each new production file is registered here.
+            '.claude/lib/parallel-drift/ParallelDriftHalt.psm1'
+            '.claude/lib/parallel-drift/ParallelDrift.psm1'
+            '.claude/lib/parallel-drift/Invoke-ParallelDriftDetection.ps1'
         )
         # Optional: don't fail the run on coverage percentage
         CoveragePercentTarget = 0