chore: align agent and instruction files with single-PR commit-slicing model

- Rewrote commit slicing guidance in Management, Planning, and subagent
  instruction files to enforce one-feature-one-PR with ordered logical commits
- Removed multi-PR branching logic from the execution workflow
- Prevents partial feature merges that cause user confusion on self-hosted tools
- All cross-references now use "Commit N" instead of "PR-N"

.github/agents/Management.agent.md

@@ -43,7 +43,7 @@ You are "lazy" in the smartest way possible. You never do what a subordinate can
     -   **Identify Goal**: Understand the user's request.
     -   **STOP**: Do not look at the code. Do not run `list_dir`. No code is to be changed or implemented until there is a fundamentally sound plan of action that has been approved by the user.
     -   **Action**: Immediately call `Planning` subagent.
-        -   *Prompt*: "Research the necessary files for '{user_request}' and write a comprehensive plan detailing as many specifics as possible to `docs/plans/current_spec.md`. Be an artist with directions and discriptions. Include file names, function names, and component names wherever possible. Break the plan into phases based on the least amount of requests. Include a Commit Slicing Strategy section that decides whether to split work into multiple PRs and, when split, defines PR-1/PR-2/PR-3 scope, dependencies, and acceptance criteria. Review and suggest updaetes to `.gitignore`, `codecov.yml`, `.dockerignore`, and `Dockerfile` if necessary. Return only when the plan is complete."
+        -   *Prompt*: "Research the necessary files for '{user_request}' and write a comprehensive plan detailing as many specifics as possible to `docs/plans/current_spec.md`. Be an artist with directions and discriptions. Include file names, function names, and component names wherever possible. Break the plan into phases based on the least amount of requests. Include a Commit Slicing Strategy section that organizes work into logical commits within a single PR — one feature = one PR, with ordered commits (Commit 1, Commit 2, …) each defining scope, files, dependencies, and validation gates. Review and suggest updaetes to `.gitignore`, `codecov.yml`, `.dockerignore`, and `Dockerfile` if necessary. Return only when the plan is complete."
     - **Task Specifics**:
         - If the task is to just run tests or audits, there is no need for a plan. Directly call `QA_Security` to perform the tests and write the report. If issues are found, return to `Planning` for a remediation plan and delegate the fixes to the corresponding subagents.
 
@@ -59,15 +59,13 @@ You are "lazy" in the smartest way possible. You never do what a subordinate can
     -   **Ask**: "Plan created. Shall I authorize the construction?"
 
 4. **Phase 4: Execution (Waterfall)**:
-        - **Single-PR or Multi-PR Decision**: Read the Commit Slicing Strategy in `docs/plans/current_spec.md`.
-        - **If single PR**:
+        - **Read Commit Slicing Strategy**: Read the Commit Slicing Strategy in `docs/plans/current_spec.md` to understand the ordered commits.
+        - **Single PR, Multiple Commits**: All work ships as one PR. Each commit maps to a phase in the plan.
             - **Backend**: Call `Backend_Dev` with the plan file.
             - **Frontend**: Call `Frontend_Dev` with the plan file.
-        - **If multi-PR**:
-            - Execute in PR slices, one slice at a time, in dependency order.
-            - Require each slice to pass review + QA gates before starting the next slice.
-            - Keep every slice deployable and independently testable.
-        - **MANDATORY**: Implementation agents must perform linting and type checks locally before declaring their slice "DONE". This is a critical step that must not be skipped to avoid broken commits and security issues.
+        - Execute commits in dependency order. Each commit must pass its validation gates before the next commit begins.
+        - The PR is merged only when all commits are complete and all DoD gates pass.
+        - **MANDATORY**: Implementation agents must perform linting and type checks locally before declaring their commit "DONE". This is a critical step that must not be skipped to avoid broken commits and security issues.
 
 5. **Phase 5: Review**:
     - **Supervisor**: Call `Supervisor` to review the implementation against the plan. Provide feedback and ensure alignment with best practices.
@@ -80,7 +78,7 @@ You are "lazy" in the smartest way possible. You never do what a subordinate can
     - **Docs**: Call `Docs_Writer`.
     - **Manual Testing**: create a new test plan in `docs/issues/*.md` for tracking manual testing focused on finding potential bugs of the implemented features.
     - **Final Report**: Summarize the successful subagent runs.
-    - **PR Roadmap**: If split mode was used, include a concise roadmap of completed and remaining PR slices.
+    - **Commit Roadmap**: Include a concise summary of completed and remaining commits within the PR.
 
 **Mandatory Commit Message**: When you reach a stopping point, provide a copy and paste code block commit message at the END of the response on format laid out in `.github/instructions/commit-message.instructions.md`
         - **STRICT RULES**:

.github/agents/Planning.agent.md

@@ -38,7 +38,7 @@ You are a PRINCIPAL ARCHITECT responsible for technical planning and system desi
    - Specify database schema changes
    - Document component interactions and data flow
    - Identify potential risks and mitigation strategies
-   - Determine PR sizing and whether to split the work into multiple PRs for safer and faster review
+   - Determine commit sizing and how to organize work into logical commits within a single PR for safer and faster review
 
 3. **Documentation**:
    - Write plan to `docs/plans/current_spec.md`
@@ -46,10 +46,10 @@ You are a PRINCIPAL ARCHITECT responsible for technical planning and system desi
    - Break down into implementable tasks using examples, diagrams, and tables
    - Estimate complexity for each component
     - Add a **Commit Slicing Strategy** section with:
-       - Decision: single PR or multiple PRs
+       - Decision: single PR with ordered logical commits (one feature = one PR)
        - Trigger reasons (scope, risk, cross-domain changes, review size)
-       - Ordered PR slices (`PR-1`, `PR-2`, ...), each with scope, files, dependencies, and validation gates
-       - Rollback and contingency notes per slice
+       - Ordered commits (`Commit 1`, `Commit 2`, ...), each with scope, files, dependencies, and validation gates
+       - Rollback and contingency notes for the PR as a whole
 
 4. **Handoff**:
    - Once plan is approved, delegate to `Supervisor` agent for review.

.github/instructions/subagent.instructions.md

@@ -23,21 +23,21 @@ runSubagent({
 
 - Validate: `plan_file` exists and contains a `Handoff Contract` JSON.
 - Kickoff: call `Planning` to create the plan if not present.
-- Decide: check if work should be split into multiple PRs (size, risk, cross-domain impact).
+- Decide: check how to organize work into logical commits within a single PR (size, risk, cross-domain impact).
 - Run: execute `Backend Dev` then `Frontend Dev` sequentially.
 - Parallel: run `QA and Security`, `DevOps` and `Doc Writer` in parallel for CI / QA checks and documentation.
 - Return: a JSON summary with `subagent_results`, `overall_status`, and aggregated artifacts.
 
 2.1) Multi-Commit Slicing Protocol
 
-- If a task is large or high-risk, split into PR slices and execute in order.
-- Each slice must have:
+- All work for a single feature ships as one PR with ordered logical commits.
+- Each commit must have:
   - Scope boundary (what is included/excluded)
-  - Dependency on previous slices
-  - Validation gates (tests/scans required for that slice)
-  - Explicit rollback notes
-- Do not start the next slice until the current slice is complete and verified.
-- Keep each slice independently reviewable and deployable.
+  - Dependency on previous commits
+  - Validation gates (tests/scans required for that commit)
+  - Explicit rollback notes for the PR as a whole
+- Do not start the next commit until the current commit is complete and verified.
+- Keep each commit independently reviewable within the PR.
 
 3) Return Contract that all subagents must return
 
@@ -55,7 +55,7 @@ runSubagent({
 
 - On a subagent failure, the Management agent must capture `tests.output` and decide to retry (1 retry maximum), or request a revert/rollback.
 - Clearly mark the `status` as `failed`, and include `errors` and `failing_tests` in the `summary`.
-- For multi-PR execution, mark failed slice as blocked and stop downstream slices until resolved.
+- For multi-commit execution, mark failed commit as blocked and stop downstream commits until resolved.
 
 5) Example: Run a full Feature Implementation